!pip -q install ./python
The environment is already saved in the Workspace and can be accessed at the file path provided below.
from unityagents import UnityEnvironment
import numpy as np
env = UnityEnvironment(file_name="/data/Tennis_Linux_NoVis/Tennis")
INFO:unityagents:
'Academy' started successfully!
Unity Academy name: Academy
Number of Brains: 1
Number of External Brains : 1
Lesson number : 0
Reset Parameters :
Unity brain name: TennisBrain
Number of Visual Observations (per agent): 0
Vector Observation space type: continuous
Vector Observation space size (per agent): 8
Number of stacked Vector Observation: 3
Vector Action space type: continuous
Vector Action space size (per agent): 2
Vector Action descriptions: ,
Environments contain brains which are responsible for deciding the actions of their associated agents. Here we check for the first brain available, and set it as the default brain we will be controlling from Python.
# get the default brain
brain_name = env.brain_names[0]
brain = env.brains[brain_name]
Run the code cell below to print some information about the environment.
# reset the environment
env_info = env.reset(train_mode=True)[brain_name]
# number of agents
num_agents = len(env_info.agents)
print('Number of agents:', num_agents)
# size of each action
action_size = brain.vector_action_space_size
print('Size of each action:', action_size)
# examine the state space
states = env_info.vector_observations
state_size = states.shape[1]
print('states.shape = ', states.shape)
print('There are {} agents. Each observes a state with length: {}'.format(states.shape[0], state_size))
print('The state for the first agent looks like:', states[0])
Number of agents: 2 Size of each action: 2 states.shape = (2, 24) There are 2 agents. Each observes a state with length: 24 The state for the first agent looks like: [ 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. -6.65278625 -1.5 -0. 0. 6.83172083 6. -0. 0. ]
In the next code cell, you will learn how to use the Python API to control the agent and receive feedback from the environment.
Note that in this coding environment, you will not be able to watch the agents while they are training, and you should set train_mode=True to restart the environment.
for i in range(5): # play game for 5 episodes
env_info = env.reset(train_mode=False)[brain_name] # reset the environment
states = env_info.vector_observations # get the current state (for each agent)
scores = np.zeros(num_agents) # initialize the score (for each agent)
while True:
actions = np.random.randn(num_agents, action_size) # select an action (for each agent)
actions = np.clip(actions, -1, 1) # all actions between -1 and 1
env_info = env.step(actions)[brain_name] # send all actions to tne environment
next_states = env_info.vector_observations # get next state (for each agent)
rewards = env_info.rewards # get reward (for each agent)
dones = env_info.local_done # see if episode finished
scores += env_info.rewards # update the score (for each agent)
states = next_states # roll over states to next time step
if np.any(dones): # exit loop if episode finished
break
print('Total score (averaged over agents) this episode: {}'.format(np.mean(scores)))
Total score (averaged over agents) this episode: 0.04500000085681677 Total score (averaged over agents) this episode: -0.004999999888241291 Total score (averaged over agents) this episode: -0.004999999888241291 Total score (averaged over agents) this episode: -0.004999999888241291 Total score (averaged over agents) this episode: -0.004999999888241291
When finished, you can close the environment.
#env.close()
Now it's your turn to train your own agent to solve the environment! A few important notes:
train_mode=True, so that the line for resetting the environment looks like the following:env_info = env.reset(train_mode=True)[brain_name]
We attempt to apply the MADDPG algorithm, potentially with a couple of adjustments, as described in the paper Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
Each agent will have its own Critic neural network, to evaluate the policy (output an estimate of the Q value given an input state), and its own Actor network being the trained policy (output an action vector given an input state). Critic networks of all agents will be trained based on the same input experiences tuples (state, next state, action agent 1, action agent 2, reward agent 1, reward agent 2), where state and next state describe the environment state and stateof both agents. That's why the paper talks about having a "centralized critic". Agent networks are trained based on the local observation of each agent.
As for DDPG, we maintain both an online and a target network for each Actor and each Critic network. The "online" network is the network being trained, while the target network is a copy of the online network from N steps before remaining unchanged for a couple of steps to serve as target in the loss expression.
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import random
from collections import deque
full_state_size = num_agents * state_size
full_action_size = num_agents * action_size
print('Full state size: ', full_state_size)
print('Full action size: ', full_action_size)
Full state size: 48 Full action size: 4
class Actor(nn.Module):
def __init__(self, actor_state_size, actor_action_size):
super(Actor, self).__init__()
self.actor_state_size = actor_state_size
self.hidden1 = nn.Sequential(
nn.Linear(actor_state_size, 300),
#nn.Dropout(0.2),
nn.ReLU()
)
self.hidden2 = nn.Sequential(
nn.Linear(300, 300),
#nn.Dropout(0.2),
nn.ReLU()
)
self.output = nn.Sequential(
nn.Linear(300, actor_action_size),
nn.Tanh()
)
def forward(self, x):
batch_size = x.shape[0]
assert(x.shape == (batch_size, self.actor_state_size))
x = self.hidden1(x)
x = self.hidden2(x)
return self.output(x)
class Critic(nn.Module):
def __init__(self, actor_state_size, actor_action_size, nb_agents):
super(Critic, self).__init__()
self.nb_agents = nb_agents
self.actor_state_size = actor_state_size
self.actor_action_size = actor_action_size
self.hidden1s = nn.Sequential(
nn.Linear(nb_agents*actor_state_size, 100),
#nn.Dropout(0.2)
#nn.ReLU()
)
self.hidden1 = nn.Sequential(
nn.Linear(100+nb_agents*actor_action_size, 300),
#nn.Dropout(0.2),
nn.ReLU()
)
self.hidden2 = nn.Sequential(
nn.Linear(300, 200),
#nn.Dropout(0.2),
nn.ReLU()
)
self.output = nn.Sequential(
nn.Linear(200, 1)
)
def forward(self, states, actions):
batch_size = states.shape[0]
assert(states.shape == (batch_size, self.nb_agents, self.actor_state_size))
assert(actions.shape == (batch_size, self.nb_agents, self.actor_action_size))
flattened_states = states.flatten(start_dim=1)
flattened_actions = actions.flatten(start_dim=1)
xs = self.hidden1s(flattened_states.float())
x = self.hidden1(torch.cat((xs, flattened_actions), dim=1))
x = self.hidden2(x)
return self.output(x)
import copy
class OUNoise:
"""Ornstein-Uhlenbeck process."""
def __init__(self, size, seed, mu=0., theta=0.15, sigma=0.5):
"""Initialize parameters and noise process."""
self.mu = mu * np.ones(size)
self.theta = theta
self.sigma = sigma
self.seed = random.seed(seed)
self.reset()
def reset(self):
"""Reset the internal state (= noise) to mean (mu)."""
self.state = copy.copy(self.mu)
def sample(self, decay_factor=1.0):
"""Update internal state and return it as a noise sample."""
x = self.state
#dx = self.theta * (self.mu - x) + self.sigma * np.array([random.random() for i in range(len(x))])
decay_factor = max(decay_factor, 0.01)
dx = decay_factor * (self.theta * (self.mu - x) + self.sigma * np.random.randn(len(x)))
self.state = x + dx
return self.state
from collections import namedtuple
UPDATE_EVERY = 20
NB_UPDATES = 5
LR_ACTOR = 3e-5
LR_CRITIC = 3e-5
TAU = 1e-2 # for soft update of target parameters
BUFFER_SIZE = 10000
NetworkTuple = namedtuple('NetworkTuple', ['online', 'target', 'optimizer'])
class Agent():
def __init__(self, batch_size, seed, nb_agents, state_size, action_size):
self.seed = random.seed(seed)
self.batch_size = batch_size
self.critics = []
self.actors = []
self.nb_agents = nb_agents
self.state_size = state_size
self.action_size = action_size
self.t_step = 0
for i in range(nb_agents):
critic_online = Critic(state_size, action_size, nb_agents).to(device)
critic_target = Critic(state_size, action_size, nb_agents).to(device)
optimizer_critic = optim.Adam(critic_online.parameters(), lr=LR_CRITIC)
actor_online = Actor(state_size, action_size).to(device)
actor_target = Actor(state_size, action_size).to(device)
optimizer_actor = optim.Adam(actor_online.parameters(), lr=LR_ACTOR)
self.critics.append(NetworkTuple(critic_online, critic_target, optimizer_critic))
self.actors.append(NetworkTuple(actor_online, actor_target, optimizer_actor))
self.experiences_buffer = deque(maxlen=BUFFER_SIZE)
self.noise = OUNoise((nb_agents, action_size), seed)
def act(self, local_states, i_episode, add_noise=True):
for actor in self.actors:
actor.online.eval()
with torch.no_grad():
actions = []
for actor, local_state in zip(self.actors, local_states):
action = actor.online(local_state.unsqueeze(0))
actions.append(action.squeeze(0).cpu().data.numpy())
actions = np.stack(actions)
for actor in self.actors:
actor.online.train()
if add_noise:
actions += self.noise.sample(0.999**i_episode)
return np.clip(actions, -1, 1)
def step(self, states, actions, next_states, rewards, done):
self.experiences_buffer.append((states, actions, next_states, rewards, done))
self.t_step += 1
if (len(self.experiences_buffer) >= self.batch_size) and (self.t_step % UPDATE_EVERY == 0):
critic_losses = []
actor_losses = []
for i in range(NB_UPDATES):
experiences = self.collect_experiences()
for j in range(self.nb_agents):
loss_critic, loss_actor = self.learn(experiences, 0.99, self.t_step, j)
critic_losses.append(loss_critic)
actor_losses.append(loss_actor)
print('Avg critic losses: ', torch.mean(torch.vstack(critic_losses)))
print('Avg actor losses: ', torch.mean(torch.vstack(actor_losses)))
for actor, critic in zip(self.actors, self.critics):
self.soft_update(critic.online, critic.target, TAU)
self.soft_update(actor.online, actor.target, TAU)
self.noise.reset()
def reset(self):
#self.t_step = 0
#self.noise.reset()
pass
def learn(self, experiences, gamma, t_step, agent_idx):
states = (torch.stack([e[0] for e in experiences])).float().to(device)
actions = (torch.stack([e[1] for e in experiences])).float().to(device)
next_states = (torch.stack([e[2] for e in experiences])).float().to(device)
rewards = (torch.vstack([e[3] for e in experiences])).float().to(device)
dones = (torch.vstack([e[4] for e in experiences])).float().to(device)
assert(states.shape == (self.batch_size, self.nb_agents, self.state_size))
assert(actions.shape == (self.batch_size, self.nb_agents, self.action_size))
assert(next_states.shape == (self.batch_size, self.nb_agents, self.state_size))
assert(rewards.shape == (self.batch_size, self.nb_agents))
critic = self.critics[agent_idx]
actor = self.actors[agent_idx]
assert(states.shape == (self.batch_size, self.nb_agents, self.state_size))
assert(next_states.shape == (self.batch_size, self.nb_agents, self.state_size))
states_t = states.transpose(0, 1)
next_states_t = next_states.transpose(0, 1)
assert(states_t.shape == (self.nb_agents, self.batch_size, self.state_size))
assert(next_states_t.shape == (self.nb_agents, self.batch_size, self.state_size))
# Train critic
next_actions = torch.stack([actor.target(next_state) for actor, next_state in zip(self.actors, next_states_t)]).transpose(0, 1).detach()
reward = rewards[:, agent_idx].reshape((batch_size, -1)).detach()
Q_target_next = critic.target(next_states, next_actions).detach()
Q_target = reward + (gamma * Q_target_next * (1 - dones)).detach()
Q_online = critic.online(states, actions)
assert(Q_online.shape == (batch_size, 1))
assert(Q_online.shape == Q_target.shape)
loss_critic = F.smooth_l1_loss(Q_online, Q_target)
critic.optimizer.zero_grad()
loss_critic.backward(retain_graph=True)
critic.optimizer.step()
# Train actor
predicted_actions = torch.stack([actor.online(state) for actor, state in zip(self.actors, states_t)]).transpose(0, 1)
actor.optimizer.zero_grad()
loss_actor = -critic.online(states, predicted_actions).mean()
#loss_actor = -critic.online(states, predicted_actions).sum()
loss_actor.backward(inputs=list(actor.online.parameters()), retain_graph=True)
actor.optimizer.step()
return (loss_critic, loss_actor)
def collect_experiences(self):
experiences = random.choices(self.experiences_buffer, k=self.batch_size)
return experiences
def soft_update(self, local_model, target_model, tau):
for target_param, local_param in zip(target_model.parameters(), local_model.parameters()):
target_param.data.copy_(tau*local_param.data + (1.0-tau)*target_param.data)
from collections import namedtuple
UPDATE_EVERY = 5
NB_UPDATES = 5
LR_ACTOR = 5e-5
LR_CRITIC = 5e-5
TAU = 5e-2 # for soft update of target parameters
BUFFER_SIZE = 100000
NetworkTuple = namedtuple('NetworkTuple', ['online', 'target', 'optimizer'])
class AgentV2():
def __init__(self, batch_size, seed, nb_agents, state_size, action_size):
self.seed = random.seed(seed)
self.batch_size = batch_size
self.actors = []
self.nb_agents = nb_agents
self.state_size = state_size
self.action_size = action_size
self.t_step = 0
self.critic_online = Critic(state_size, action_size, nb_agents).to(device)
self.critic_target = Critic(state_size, action_size, nb_agents).to(device)
self.optimizer_critic = optim.Adam(self.critic_online.parameters(), lr=LR_CRITIC)
for i in range(nb_agents):
actor_online = Actor(state_size, action_size).to(device)
actor_target = Actor(state_size, action_size).to(device)
optimizer_actor = optim.Adam(actor_online.parameters(), lr=LR_ACTOR)
self.actors.append(NetworkTuple(actor_online, actor_target, optimizer_actor))
self.experiences_buffer = deque(maxlen=BUFFER_SIZE)
self.noise = OUNoise((nb_agents, action_size), seed)
def act(self, local_states, i_episode, add_noise=True):
for actor in self.actors:
actor.online.eval()
with torch.no_grad():
actions = []
for actor, local_state in zip(self.actors, local_states):
action = actor.online(local_state.unsqueeze(0))
actions.append(action.squeeze(0).cpu().data.numpy())
actions = np.stack(actions)
for actor in self.actors:
actor.online.train()
if add_noise:
actions += self.noise.sample(0.999**i_episode)
return np.clip(actions, -1, 1)
def step(self, states, actions, next_states, rewards, done):
self.experiences_buffer.append((states, actions, next_states, rewards, done))
self.t_step += 1
if (len(self.experiences_buffer) >= self.batch_size) and (self.t_step % UPDATE_EVERY == 0):
critic_losses = []
actor_losses = []
for i in range(NB_UPDATES):
experiences = self.collect_experiences()
loss_critic, loss_actor = self.learn(experiences, 0.99, self.t_step)
critic_losses.append(loss_critic)
actor_losses.append(loss_actor)
print('Avg critic losses: ', torch.mean(torch.vstack(critic_losses)))
print('Avg actor losses: ', torch.mean(torch.vstack(actor_losses)))
for actor in self.actors:
self.soft_update(actor.online, actor.target, TAU)
self.soft_update(self.critic_online, self.critic_target, TAU)
self.noise.reset()
def reset(self):
#self.t_step = 0
self.noise.reset()
def learn(self, experiences, gamma, t_step):
states = (torch.stack([e[0] for e in experiences])).float().to(device)
actions = (torch.stack([e[1] for e in experiences])).float().to(device)
next_states = (torch.stack([e[2] for e in experiences])).float().to(device)
rewards = (torch.vstack([e[3] for e in experiences])).float().to(device)
dones = (torch.vstack([e[4] for e in experiences])).float().to(device)
assert(states.shape == (self.batch_size, self.nb_agents, self.state_size))
assert(actions.shape == (self.batch_size, self.nb_agents, self.action_size))
assert(next_states.shape == (self.batch_size, self.nb_agents, self.state_size))
assert(rewards.shape == (self.batch_size, self.nb_agents))
assert(dones.shape == (self.batch_size, self.nb_agents))
assert(states.shape == (self.batch_size, self.nb_agents, self.state_size))
assert(next_states.shape == (self.batch_size, self.nb_agents, self.state_size))
states_t = states.transpose(0, 1)
next_states_t = next_states.transpose(0, 1)
assert(states_t.shape == (self.nb_agents, self.batch_size, self.state_size))
assert(next_states_t.shape == (self.nb_agents, self.batch_size, self.state_size))
# Train centralized critic
next_actions = torch.stack([actor.target(next_state) for actor, next_state in zip(self.actors, next_states_t)]).transpose(0, 1).detach()
Q_target_next = self.critic_target(next_states, next_actions).detach()
with torch.no_grad():
Q_target = torch.hstack([rewards[:, i].unsqueeze(1) + (gamma * Q_target_next * (1 - dones[:, i].unsqueeze(1))) for i in range(self.nb_agents)])
#Q_target = rewards + (gamma * Q_target_next * (1 - dones)).detach()
Q_online = self.critic_online(states, actions)
assert(Q_online.shape == (batch_size, 1))
assert(Q_target.shape == (batch_size, self.nb_agents))
self.optimizer_critic.zero_grad()
#loss_critic = torch.Tensor([0])
#for i in range(self.nb_agents):
# loss_critic += F.smooth_l1_loss(Q_online, Q_target[:, i].unsqueeze(1)) / self.nb_agents
loss_critic = F.smooth_l1_loss(Q_online.expand(batch_size, self.nb_agents), Q_target)
loss_critic.backward(retain_graph=True)
self.optimizer_critic.step()
loss_actor = torch.Tensor([0])
# Train actors
for idx_agent in range(self.nb_agents):
actor = self.actors[idx_agent]
actor.optimizer.zero_grad()
detachv = [lambda t: t if i == idx_agent else t.detach() for i in range(self.nb_agents)]
#predicted_actions = torch.stack([d(actor.online(state)) for d, actor, state in zip(detachv, self.actors, states_t)]).transpose(0, 1)
predicted_actions = torch.stack([actor.online(state) for actor, state in zip(self.actors, states_t)]).transpose(0, 1)
loss_actor = -self.critic_online(states, predicted_actions).mean()
loss_actor.backward(inputs=list(actor.online.parameters()), retain_graph=True)
#loss_actor.backward(retain_graph=True)
actor.optimizer.step()
return (loss_critic, loss_actor)
def collect_experiences(self):
experiences = random.choices(self.experiences_buffer, k=self.batch_size)
return experiences
def soft_update(self, local_model, target_model, tau):
for target_param, local_param in zip(target_model.parameters(), local_model.parameters()):
target_param.data.copy_(tau*local_param.data + (1.0-tau)*target_param.data)
from collections import namedtuple
UPDATE_EVERY = 1
NB_UPDATES = 1
LR_ACTOR = 5e-5
LR_CRITIC = 5e-5
TAU = 1e-2 # for soft update of target parameters
BUFFER_SIZE = 100000
NetworkTuple = namedtuple('NetworkTuple', ['online', 'target', 'optimizer'])
# Variant of AgentV2 with a single actor
class AgentV3():
def __init__(self, batch_size, seed, nb_agents, state_size, action_size):
self.seed = random.seed(seed)
self.batch_size = batch_size
self.actors = []
self.nb_agents = nb_agents
self.state_size = state_size
self.action_size = action_size
self.t_step = 0
self.critic_online = Critic(state_size, action_size, nb_agents).to(device)
self.critic_target = Critic(state_size, action_size, nb_agents).to(device)
self.critic_online.train()
self.critic_target.eval()
self.optimizer_critic = optim.Adam(self.critic_online.parameters(), lr=LR_CRITIC)
self.actor_online = Actor(state_size, action_size).to(device)
self.actor_target = Actor(state_size, action_size).to(device)
self.actor_online.train()
self.actor_target.eval()
self.optimizer_actor = optim.Adam(self.actor_online.parameters(), lr=LR_ACTOR)
self.experiences_buffer = deque(maxlen=BUFFER_SIZE)
self.noise = OUNoise((nb_agents, action_size), seed)
def act(self, local_states, i_episode, add_noise=True):
self.actor_online.eval()
with torch.no_grad():
actions = np.stack([self.actor_online(local_state.unsqueeze(0)).squeeze(0).cpu().data.numpy() for local_state in local_states])
self.actor_online.train()
if add_noise:
actions += self.noise.sample(0.999**i_episode)
return np.clip(actions, -1, 1)
def step(self, states, actions, next_states, rewards, done):
self.experiences_buffer.append((states, actions, next_states, rewards, done))
self.t_step += 1
if (len(self.experiences_buffer) >= self.batch_size) and (self.t_step % UPDATE_EVERY == 0):
critic_losses = []
actor_losses = []
for i in range(NB_UPDATES):
experiences = self.collect_experiences()
loss_critic, loss_actor = self.learn(experiences, 0.99, self.t_step)
critic_losses.append(loss_critic)
actor_losses.append(loss_actor)
print('Avg critic losses: ', torch.mean(torch.vstack(critic_losses)))
print('Avg actor losses: ', torch.mean(torch.vstack(actor_losses)))
self.soft_update(self.actor_online, self.actor_target, TAU)
self.soft_update(self.critic_online, self.critic_target, TAU)
self.noise.reset()
def reset(self):
#self.t_step = 0
self.noise.reset()
def learn(self, experiences, gamma, t_step):
states = (torch.stack([e[0] for e in experiences])).float().to(device)
actions = (torch.stack([e[1] for e in experiences])).float().to(device)
next_states = (torch.stack([e[2] for e in experiences])).float().to(device)
rewards = (torch.vstack([e[3] for e in experiences])).float().to(device)
dones = (torch.vstack([e[4] for e in experiences])).float().to(device)
assert(states.shape == (self.batch_size, self.nb_agents, self.state_size))
assert(actions.shape == (self.batch_size, self.nb_agents, self.action_size))
assert(next_states.shape == (self.batch_size, self.nb_agents, self.state_size))
assert(rewards.shape == (self.batch_size, self.nb_agents))
assert(dones.shape == (self.batch_size, self.nb_agents))
assert(states.shape == (self.batch_size, self.nb_agents, self.state_size))
assert(next_states.shape == (self.batch_size, self.nb_agents, self.state_size))
states_t = states.transpose(0, 1)
next_states_t = next_states.transpose(0, 1)
assert(states_t.shape == (self.nb_agents, self.batch_size, self.state_size))
assert(next_states_t.shape == (self.nb_agents, self.batch_size, self.state_size))
# Train centralized critic
next_actions = torch.stack([self.actor_target(next_state) for next_state in next_states_t]).transpose(0, 1).detach()
Q_target_next = self.critic_target(next_states, next_actions).detach()
with torch.no_grad():
Q_target = torch.hstack([rewards[:, i].unsqueeze(1) + (gamma * Q_target_next * (1 - dones[:, i].unsqueeze(1))) for i in range(self.nb_agents)])
Q_online = self.critic_online(states, actions)
assert(Q_online.shape == (batch_size, 1))
assert(Q_target.shape == (batch_size, self.nb_agents))
self.optimizer_critic.zero_grad()
loss_critic = F.smooth_l1_loss(Q_online.expand(batch_size, self.nb_agents), Q_target)
loss_critic.backward()
self.optimizer_critic.step()
loss_actor = torch.Tensor([0])
# Train actor
self.optimizer_actor.zero_grad()
predicted_actions = torch.stack([self.actor_online(state) for state in states_t]).transpose(0, 1)
loss_actor = -self.critic_online(states, predicted_actions).mean()
loss_actor.backward()
self.optimizer_actor.step()
return (loss_critic, loss_actor)
def collect_experiences(self):
experiences = random.choices(self.experiences_buffer, k=self.batch_size)
return experiences
def soft_update(self, local_model, target_model, tau):
for target_param, local_param in zip(target_model.parameters(), local_model.parameters()):
target_param.data.copy_(tau*local_param.data + (1.0-tau)*target_param.data)
def run_episode(agent, i_episode, num_agents):
env_info = env.reset(train_mode=True)[brain_name]
scores = np.zeros(num_agents)
states = torch.from_numpy(env_info.vector_observations).float().to(device)
i = 0
while True: # episodic task => no need to cap the number of time steps
actions = agent.act(states, i_episode)
env_info = env.step(actions)[brain_name]
next_states = torch.from_numpy(env_info.vector_observations).float().to(device)
rewards = torch.FloatTensor(env_info.rewards).to(device)
dones = torch.FloatTensor(env_info.local_done).to(device)
agent.step(states, torch.from_numpy(actions).float().to(device), next_states, rewards, dones)
scores += env_info.rewards
states = next_states
if np.any(env_info.local_done):
print('episode done in ', i, ' time steps; scores: ', scores)
break
i += 1
episode_score = np.max(scores)
return episode_score
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
batch_size = 256
seed = 10
agent = AgentV3(batch_size, seed, num_agents, state_size, action_size)
from workspace_utils import keep_awake
torch.autograd.set_detect_anomaly(True)
n_episodes = 4000
all_scores = []
last_scores = deque(maxlen=100)
MIN_AVG_SCORE = 0.5
max_mean_score = -10.0
for i in keep_awake(range(n_episodes)):
agent.reset()
episode_score = run_episode(agent, i, 2)
last_scores.append(episode_score)
mean_score = np.mean(np.array(last_scores))
all_scores.append(episode_score)
print("Episode ", i, " - Score: ", episode_score)
if i > 0 and i % 20 == 0:
print("Episode ", i, " - Mean score: ", mean_score)
if mean_score > max_mean_score:
max_mean_score = mean_score
torch.save(agent.actor_online.state_dict(), f'checkpoint_actor.pth')
torch.save(agent.critic_online.state_dict(), f'checkpoint_critic.pth')
if i > 100 and mean_score >= MIN_AVG_SCORE:
print("Problem solved!")
break
episode done in 14 time steps; scores: [ 0. -0.01] Episode 0 - Score: 0.0 episode done in 12 time steps; scores: [ 0. -0.01] Episode 1 - Score: 0.0 episode done in 14 time steps; scores: [ 0. -0.01] Episode 2 - Score: 0.0 episode done in 13 time steps; scores: [ 0. -0.01] Episode 3 - Score: 0.0 episode done in 13 time steps; scores: [ 0. -0.01] Episode 4 - Score: 0.0 episode done in 13 time steps; scores: [-0.01 0. ] Episode 5 - Score: 0.0 episode done in 13 time steps; scores: [ 0. -0.01] Episode 6 - Score: 0.0 episode done in 14 time steps; scores: [-0.01 0. ] Episode 7 - Score: 0.0 episode done in 29 time steps; scores: [ 0. 0.09] Episode 8 - Score: 0.0900000017136 episode done in 13 time steps; scores: [ 0. -0.01] Episode 9 - Score: 0.0 episode done in 13 time steps; scores: [ 0. -0.01] Episode 10 - Score: 0.0 episode done in 13 time steps; scores: [ 0. -0.01] Episode 11 - Score: 0.0 episode done in 14 time steps; scores: [ 0. -0.01] Episode 12 - Score: 0.0 episode done in 13 time steps; scores: [ 0. -0.01] Episode 13 - Score: 0.0 episode done in 13 time steps; scores: [ 0. -0.01] Episode 14 - Score: 0.0 episode done in 13 time steps; scores: [ 0. -0.01] Episode 15 - Score: 0.0 Avg critic losses: tensor(0.2044, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.2659, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.1570, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.1634, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 16 - Score: 0.0 Avg critic losses: tensor(0.1107, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.1361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0788, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0490, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0371, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.1067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0301, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.1558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0189, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.2006, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0153, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.2209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0222, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.2492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0278, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.2755, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0364, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.3424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0310, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.3378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0306, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.3227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0347, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.3105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0266, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.2838, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0240, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.2889, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 17 - Score: 0.0 Avg critic losses: tensor(0.0207, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.2690, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0189, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.2459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0193, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.2420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0098, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.2020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0126, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.1887, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0098, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.1786, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0069, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.1474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0089, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.1218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0074, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.1209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0057, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.1001, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0073, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0072, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0742, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0082, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0690, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0077, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0461, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 18 - Score: 0.0 Avg critic losses: tensor(0.0083, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0078, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0657, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0082, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0661, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0072, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0070, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0701, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0062, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0706, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0038, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0935, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0043, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0856, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0044, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0938, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0043, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0946, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0049, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.1067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0050, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.1163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0042, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.1119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0035, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.1103, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 19 - Score: 0.0 Avg critic losses: tensor(0.0038, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.1020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0033, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.1030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0036, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0970, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0042, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0935, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0023, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0863, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0028, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0840, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0032, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0798, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0032, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0673, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0029, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0705, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0030, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0023, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0618, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0025, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0031, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0039, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0303, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 20 - Score: 0.0 Episode 20 - Mean score: 0.00428571436732 Avg critic losses: tensor(0.0026, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0034, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0024, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0021, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0024, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0033, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0030, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0022, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0024, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0018, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0027, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0024, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0026, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0022, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0402, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 21 - Score: 0.0 Avg critic losses: tensor(0.0024, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0025, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0022, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0018, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0017, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0025, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0024, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0024, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0019, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0017, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0017, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0019, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0016, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0016, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0243, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 22 - Score: 0.0 Avg critic losses: tensor(0.0017, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0020, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0019, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0015, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0017, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0016, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0020, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0019, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0019, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0017, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0019, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0267, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 23 - Score: 0.0 Avg critic losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0017, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0017, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0016, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0016, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0018, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0017, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0018, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0017, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0019, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0239, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 24 - Score: 0.0 Avg critic losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0017, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0015, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0017, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0023, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0019, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0022, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0017, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0254, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 25 - Score: 0.0 Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0015, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0015, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0296, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 26 - Score: 0.0 Avg critic losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0015, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0159, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 27 - Score: 0.0 Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0015, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0195, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 28 - Score: 0.0 Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0015, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0247, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 29 - Score: 0.0 Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0244, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 30 - Score: 0.0 Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0326, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 31 - Score: 0.0 Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0249, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 32 - Score: 0.0 Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0268, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 33 - Score: 0.0 Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0244, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 34 - Score: 0.0 Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0325, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 35 - Score: 0.0 Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0229, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 36 - Score: 0.0 Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0247, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 37 - Score: 0.0 Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0193, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 38 - Score: 0.0 Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0230, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 39 - Score: 0.0 Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0199, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 40 - Score: 0.0 Episode 40 - Mean score: 0.00219512199302 Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0181, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 41 - Score: 0.0 Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0163, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 42 - Score: 0.0 Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0141, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 43 - Score: 0.0 Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0163, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 44 - Score: 0.0 Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0135, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 45 - Score: 0.0 Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0131, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 46 - Score: 0.0 Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0097, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 47 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0160, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 48 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0091, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 49 - Score: 0.0 Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0130, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 50 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0170, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 51 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0136, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 52 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0071, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 53 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0068, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 54 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0015, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0072, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 55 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0036, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 56 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0154, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 57 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(3.6044e-05, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-5.6075e-05, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0023, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 58 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0005, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-9.4585e-07, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-1.8756e-05, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0004, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 59 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(4.0903e-05, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0017, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0015, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 60 - Score: 0.0 Episode 60 - Mean score: 0.00147540986416 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0009, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-3.8112e-05, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0043, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 61 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0023, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 62 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0011, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0017, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0017, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0023, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0015, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0025, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 63 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0015, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0006, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(5.2091e-05, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-6.9075e-05, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 64 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0003, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0037, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 65 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0008, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0017, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0010, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0019, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 66 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0006, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0017, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0017, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0004, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0005, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 67 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0002, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0040, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 68 - Score: 0.0 Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(9.0490e-05, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0017, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0015, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0023, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0017, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 69 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0008, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0011, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0011, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0003, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0011, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 70 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0015, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0012, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 71 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0015, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0007, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-8.0844e-05, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0032, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 72 - Score: 0.0 Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0015, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(9.5150e-06, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0012, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0011, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0012, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0007, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.09 0.1 ] Episode 73 - Score: 0.10000000149 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0017, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0011, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0005, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0025, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 74 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0012, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0011, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0006, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 75 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0003, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 76 - Score: 0.0 Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0009, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0010, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 77 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 78 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0009, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 79 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0004, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 80 - Score: 0.0 Episode 80 - Mean score: 0.0023456790519 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 81 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0004, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 82 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 83 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [-0.01 0. ] Episode 84 - Score: 0.0 Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 85 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 86 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 87 - Score: 0.0 Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 88 - Score: 0.0 Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 89 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 90 - Score: 0.0 Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 91 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 92 - Score: 0.0 Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 93 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 94 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 95 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 96 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 97 - Score: 0.0 Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 98 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 99 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 100 - Score: 0.0 Episode 100 - Mean score: 0.00190000003204 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 101 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 102 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 103 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 104 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 105 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0008, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 106 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 107 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 108 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 109 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 110 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 111 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 112 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 113 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 114 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 115 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 116 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 117 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 118 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 119 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 120 - Score: 0.0 Episode 120 - Mean score: 0.0010000000149 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 121 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 122 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 123 - Score: 0.0 Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 124 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 125 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 126 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 127 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 128 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 129 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 130 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 131 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 132 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 133 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 134 - Score: 0.0 Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 135 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 136 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 137 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 138 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 139 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 140 - Score: 0.0 Episode 140 - Mean score: 0.0010000000149 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 141 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 142 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 143 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 144 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 145 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 146 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 147 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 148 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 149 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 150 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 151 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 152 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 153 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 154 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 155 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 156 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 157 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 158 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 159 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 160 - Score: 0.0 Episode 160 - Mean score: 0.0010000000149 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 161 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 162 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 163 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 164 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 165 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 166 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 167 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 168 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 169 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 170 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 171 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 172 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 173 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 174 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 175 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 176 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 177 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 178 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 179 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 180 - Score: 0.0 Episode 180 - Mean score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 181 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 182 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 183 - Score: 0.0 Avg critic losses: tensor(9.2539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 184 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 185 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 186 - Score: 0.0 Avg critic losses: tensor(8.6193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 187 - Score: 0.0 Avg critic losses: tensor(9.9502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 188 - Score: 0.0 Avg critic losses: tensor(9.3602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 189 - Score: 0.0 Avg critic losses: tensor(8.2385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 190 - Score: 0.0 Avg critic losses: tensor(7.8903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 191 - Score: 0.0 Avg critic losses: tensor(8.5101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 192 - Score: 0.0 Avg critic losses: tensor(8.8494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 193 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 194 - Score: 0.0 Avg critic losses: tensor(7.8339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 195 - Score: 0.0 Avg critic losses: tensor(9.7407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 196 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 197 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 198 - Score: 0.0 Avg critic losses: tensor(7.1374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 199 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 200 - Score: 0.0 Episode 200 - Mean score: 0.0 Avg critic losses: tensor(8.3640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 201 - Score: 0.0 Avg critic losses: tensor(8.3258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 202 - Score: 0.0 Avg critic losses: tensor(9.0947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 203 - Score: 0.0 Avg critic losses: tensor(7.3526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 204 - Score: 0.0 Avg critic losses: tensor(8.5843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 205 - Score: 0.0 Avg critic losses: tensor(7.3103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 206 - Score: 0.0 Avg critic losses: tensor(6.5020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 207 - Score: 0.0 Avg critic losses: tensor(7.8419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 208 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 209 - Score: 0.0 Avg critic losses: tensor(6.9356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 210 - Score: 0.0 Avg critic losses: tensor(7.0106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 211 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 212 - Score: 0.0 Avg critic losses: tensor(8.7405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 213 - Score: 0.0 Avg critic losses: tensor(8.7701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 214 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 215 - Score: 0.0 Avg critic losses: tensor(9.6462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 216 - Score: 0.0 Avg critic losses: tensor(7.7003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 217 - Score: 0.0 Avg critic losses: tensor(8.9347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 218 - Score: 0.0 Avg critic losses: tensor(7.9707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 219 - Score: 0.0 Avg critic losses: tensor(7.2529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 220 - Score: 0.0 Episode 220 - Mean score: 0.0 Avg critic losses: tensor(9.4157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 221 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 222 - Score: 0.0 Avg critic losses: tensor(8.3343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 223 - Score: 0.0 Avg critic losses: tensor(9.4493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 224 - Score: 0.0 Avg critic losses: tensor(6.6775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 225 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 226 - Score: 0.0 Avg critic losses: tensor(9.5768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 227 - Score: 0.0 Avg critic losses: tensor(7.7114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 228 - Score: 0.0 Avg critic losses: tensor(7.9542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 229 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 230 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 231 - Score: 0.0 Avg critic losses: tensor(6.6534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 232 - Score: 0.0 Avg critic losses: tensor(8.0587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 233 - Score: 0.0 Avg critic losses: tensor(9.5067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 234 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 235 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 236 - Score: 0.0 Avg critic losses: tensor(7.0324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 237 - Score: 0.0 Avg critic losses: tensor(7.1495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 238 - Score: 0.0 Avg critic losses: tensor(8.5199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 239 - Score: 0.0 Avg critic losses: tensor(9.5610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 240 - Score: 0.0 Episode 240 - Mean score: 0.0 Avg critic losses: tensor(6.4205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 241 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 242 - Score: 0.0 Avg critic losses: tensor(8.0876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 243 - Score: 0.0 Avg critic losses: tensor(8.0389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 244 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 245 - Score: 0.0 Avg critic losses: tensor(8.6232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 246 - Score: 0.0 Avg critic losses: tensor(8.3941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 247 - Score: 0.0 Avg critic losses: tensor(8.8624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 248 - Score: 0.0 Avg critic losses: tensor(8.6810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 249 - Score: 0.0 Avg critic losses: tensor(8.3039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 250 - Score: 0.0 Avg critic losses: tensor(6.0443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 251 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 252 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 253 - Score: 0.0 Avg critic losses: tensor(8.7213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 254 - Score: 0.0 Avg critic losses: tensor(9.3687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 255 - Score: 0.0 Avg critic losses: tensor(6.1344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 256 - Score: 0.0 Avg critic losses: tensor(6.6253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 257 - Score: 0.0 Avg critic losses: tensor(7.9340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 258 - Score: 0.0 Avg critic losses: tensor(5.6635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 259 - Score: 0.0 Avg critic losses: tensor(8.9726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 260 - Score: 0.0 Episode 260 - Mean score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 261 - Score: 0.0 Avg critic losses: tensor(8.4862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 262 - Score: 0.0 Avg critic losses: tensor(9.4075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 263 - Score: 0.0 Avg critic losses: tensor(8.2773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 264 - Score: 0.0 Avg critic losses: tensor(7.2751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 265 - Score: 0.0 Avg critic losses: tensor(8.4778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 266 - Score: 0.0 Avg critic losses: tensor(6.2302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 267 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 268 - Score: 0.0 Avg critic losses: tensor(9.4098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 269 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 270 - Score: 0.0 Avg critic losses: tensor(8.2261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 271 - Score: 0.0 Avg critic losses: tensor(7.5352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 272 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 273 - Score: 0.0 Avg critic losses: tensor(8.5875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 274 - Score: 0.0 Avg critic losses: tensor(9.4553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 275 - Score: 0.0 Avg critic losses: tensor(8.7721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 276 - Score: 0.0 Avg critic losses: tensor(7.8589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 277 - Score: 0.0 Avg critic losses: tensor(7.0720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 278 - Score: 0.0 Avg critic losses: tensor(9.5906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 279 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 280 - Score: 0.0 Episode 280 - Mean score: 0.0 Avg critic losses: tensor(7.9483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 281 - Score: 0.0 Avg critic losses: tensor(6.9465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 282 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 283 - Score: 0.0 Avg critic losses: tensor(8.5697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 284 - Score: 0.0 Avg critic losses: tensor(8.8212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 285 - Score: 0.0 Avg critic losses: tensor(7.5051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 286 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 287 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 288 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 289 - Score: 0.0 Avg critic losses: tensor(8.3157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 290 - Score: 0.0 Avg critic losses: tensor(8.6251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 291 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 292 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 293 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 294 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 295 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 296 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 297 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 298 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 299 - Score: 0.0 Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 300 - Score: 0.0 Episode 300 - Mean score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 301 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 302 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 303 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 304 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 305 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 306 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 307 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 308 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 309 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 310 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 311 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 312 - Score: 0.0 Avg critic losses: tensor(7.4239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 313 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 314 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 315 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 316 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 317 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 318 - Score: 0.0 Avg critic losses: tensor(8.7839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 319 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 320 - Score: 0.0 Episode 320 - Mean score: 0.0 Avg critic losses: tensor(9.1567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 321 - Score: 0.0 Avg critic losses: tensor(9.9418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 322 - Score: 0.0 Avg critic losses: tensor(8.6610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 323 - Score: 0.0 Avg critic losses: tensor(6.5650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 324 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 325 - Score: 0.0 Avg critic losses: tensor(8.8823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 326 - Score: 0.0 Avg critic losses: tensor(8.1842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 327 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 328 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 329 - Score: 0.0 Avg critic losses: tensor(8.5833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 330 - Score: 0.0 Avg critic losses: tensor(8.3978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 331 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 332 - Score: 0.0 Avg critic losses: tensor(7.6053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 333 - Score: 0.0 Avg critic losses: tensor(9.4112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 334 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 335 - Score: 0.0 Avg critic losses: tensor(7.3216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 336 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 337 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 338 - Score: 0.0 Avg critic losses: tensor(9.7495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 339 - Score: 0.0 Avg critic losses: tensor(7.1626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 340 - Score: 0.0 Episode 340 - Mean score: 0.0 Avg critic losses: tensor(8.7240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 341 - Score: 0.0 Avg critic losses: tensor(7.4920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 342 - Score: 0.0 Avg critic losses: tensor(6.8048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 343 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 344 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 345 - Score: 0.0 Avg critic losses: tensor(8.1203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 346 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 347 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 348 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 349 - Score: 0.0 Avg critic losses: tensor(8.1767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 350 - Score: 0.0 Avg critic losses: tensor(9.0957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 351 - Score: 0.0 Avg critic losses: tensor(9.1147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 352 - Score: 0.0 Avg critic losses: tensor(9.7105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 353 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 354 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 355 - Score: 0.0 Avg critic losses: tensor(9.7385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 356 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 357 - Score: 0.0 Avg critic losses: tensor(8.1963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 358 - Score: 0.0 Avg critic losses: tensor(9.3580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 359 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 360 - Score: 0.0 Episode 360 - Mean score: 0.0 Avg critic losses: tensor(8.9985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 361 - Score: 0.0 Avg critic losses: tensor(7.3056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 362 - Score: 0.0 Avg critic losses: tensor(7.8066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 363 - Score: 0.0 Avg critic losses: tensor(8.5435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 364 - Score: 0.0 Avg critic losses: tensor(7.6094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 365 - Score: 0.0 Avg critic losses: tensor(9.7781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 366 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 367 - Score: 0.0 Avg critic losses: tensor(9.3264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 368 - Score: 0.0 Avg critic losses: tensor(6.9023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 369 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 370 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 371 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 372 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 373 - Score: 0.0 Avg critic losses: tensor(7.2386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 374 - Score: 0.0 Avg critic losses: tensor(9.4352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 375 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 376 - Score: 0.0 Avg critic losses: tensor(7.0198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 377 - Score: 0.0 Avg critic losses: tensor(8.3827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 378 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 379 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 380 - Score: 0.0 Episode 380 - Mean score: 0.0 Avg critic losses: tensor(8.5167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 381 - Score: 0.10000000149 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 382 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 383 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 384 - Score: 0.0 Avg critic losses: tensor(9.2677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 385 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 386 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 387 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 388 - Score: 0.0 Avg critic losses: tensor(9.3396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 389 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 390 - Score: 0.0 Avg critic losses: tensor(8.0543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 391 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 392 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 393 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 394 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 395 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 396 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 397 - Score: 0.0 Avg critic losses: tensor(9.5445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 398 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 399 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 400 - Score: 0.0 Episode 400 - Mean score: 0.0010000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 401 - Score: 0.0 Avg critic losses: tensor(9.5603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 402 - Score: 0.0 Avg critic losses: tensor(7.8807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 403 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 404 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 405 - Score: 0.0 Avg critic losses: tensor(8.8118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 406 - Score: 0.0 Avg critic losses: tensor(8.4213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 407 - Score: 0.0 Avg critic losses: tensor(9.4515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 408 - Score: 0.0 Avg critic losses: tensor(7.8002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 409 - Score: 0.0 Avg critic losses: tensor(8.4840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 410 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 411 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 412 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 413 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 414 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 415 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 416 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 417 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 418 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 419 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 420 - Score: 0.0 Episode 420 - Mean score: 0.0010000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 421 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 422 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 423 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 424 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 425 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 426 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 427 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 428 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 429 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 430 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 431 - Score: 0.0 Avg critic losses: tensor(8.2320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 432 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 433 - Score: 0.0 Avg critic losses: tensor(9.7409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0010, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 434 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 435 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 436 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 437 - Score: 0.0 Avg critic losses: tensor(8.2920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 438 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 439 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 440 - Score: 0.0 Episode 440 - Mean score: 0.0010000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 441 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 442 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 443 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 444 - Score: 0.0 Avg critic losses: tensor(8.6084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 445 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 446 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 447 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 448 - Score: 0.0 Avg critic losses: tensor(9.0938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 449 - Score: 0.0 Avg critic losses: tensor(8.3004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 450 - Score: 0.0 Avg critic losses: tensor(9.1883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 451 - Score: 0.0 Avg critic losses: tensor(8.8361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 452 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 453 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 454 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 455 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 456 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 457 - Score: 0.0 Avg critic losses: tensor(9.7655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 458 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 459 - Score: 0.0 Avg critic losses: tensor(9.7343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 460 - Score: 0.0 Episode 460 - Mean score: 0.0010000000149 Avg critic losses: tensor(7.9721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [ 0. -0.01] Episode 461 - Score: 0.0 Avg critic losses: tensor(5.5708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 462 - Score: 0.0 Avg critic losses: tensor(8.5693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 463 - Score: 0.0 Avg critic losses: tensor(7.6234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 464 - Score: 0.0 Avg critic losses: tensor(9.7727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 465 - Score: 0.0 Avg critic losses: tensor(9.6820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 466 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 467 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 468 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 469 - Score: 0.0 Avg critic losses: tensor(8.5422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 470 - Score: 0.0 Avg critic losses: tensor(7.7270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 471 - Score: 0.0 Avg critic losses: tensor(7.9077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 472 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 473 - Score: 0.0900000017136 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) episode done in 17 time steps; scores: [-0.01 0. ] Episode 474 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 475 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 476 - Score: 0.0 Avg critic losses: tensor(7.3709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 477 - Score: 0.0 Avg critic losses: tensor(9.1502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 478 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 479 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 480 - Score: 0.0 Episode 480 - Mean score: 0.00190000003204 Avg critic losses: tensor(9.1107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 481 - Score: 0.0 Avg critic losses: tensor(9.2892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 482 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 483 - Score: 0.0 Avg critic losses: tensor(9.6010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 484 - Score: 0.0 Avg critic losses: tensor(8.2293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) episode done in 19 time steps; scores: [ 0. -0.01] Episode 485 - Score: 0.0 Avg critic losses: tensor(5.6618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 486 - Score: 0.0 Avg critic losses: tensor(9.7648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 487 - Score: 0.0 Avg critic losses: tensor(7.7568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 488 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 489 - Score: 0.0 Avg critic losses: tensor(6.3899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0008, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 490 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 491 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [ 0. -0.01] Episode 492 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 493 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 494 - Score: 0.0 Avg critic losses: tensor(7.1405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 495 - Score: 0.0 Avg critic losses: tensor(6.9659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 496 - Score: 0.0 Avg critic losses: tensor(9.2195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 497 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 498 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0003, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 499 - Score: 0.0 Avg critic losses: tensor(7.4712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 500 - Score: 0.0 Episode 500 - Mean score: 0.000900000017136 Avg critic losses: tensor(7.5108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 501 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(6.5271e-05, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0009, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 502 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0023, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 503 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 504 - Score: 0.0 Avg critic losses: tensor(9.2387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 505 - Score: 0.0 Avg critic losses: tensor(9.6511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 506 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 507 - Score: 0.0 Avg critic losses: tensor(8.5219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) episode done in 12 time steps; scores: [ 0. -0.01] Episode 508 - Score: 0.0 Avg critic losses: tensor(8.8555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 509 - Score: 0.0 Avg critic losses: tensor(7.8339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 510 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 511 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 512 - Score: 0.0 Avg critic losses: tensor(8.0920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 513 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 514 - Score: 0.0 Avg critic losses: tensor(6.9437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 515 - Score: 0.0 Avg critic losses: tensor(9.1342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 516 - Score: 0.0 Avg critic losses: tensor(8.0051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 517 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 518 - Score: 0.0 Avg critic losses: tensor(7.0403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 519 - Score: 0.0 Avg critic losses: tensor(8.3434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 520 - Score: 0.0 Episode 520 - Mean score: 0.000900000017136 Avg critic losses: tensor(8.5776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 521 - Score: 0.0 Avg critic losses: tensor(7.6172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 522 - Score: 0.0 Avg critic losses: tensor(7.3462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 523 - Score: 0.0 Avg critic losses: tensor(7.8459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 524 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 525 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 526 - Score: 0.0 Avg critic losses: tensor(7.8300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 527 - Score: 0.0 Avg critic losses: tensor(9.7711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 528 - Score: 0.0 Avg critic losses: tensor(8.6699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 529 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 530 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 531 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 532 - Score: 0.0 Avg critic losses: tensor(6.3908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 533 - Score: 0.0 Avg critic losses: tensor(7.2141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) episode done in 47 time steps; scores: [-0.01 0.1 ] Episode 534 - Score: 0.10000000149 Avg critic losses: tensor(8.5774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 535 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 536 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 537 - Score: 0.0 Avg critic losses: tensor(8.1524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 538 - Score: 0.0 Avg critic losses: tensor(6.9445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 539 - Score: 0.0 Avg critic losses: tensor(8.4336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 540 - Score: 0.0 Episode 540 - Mean score: 0.00280000004917 Avg critic losses: tensor(6.1549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 541 - Score: 0.0 Avg critic losses: tensor(7.6962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 542 - Score: 0.0 Avg critic losses: tensor(9.5633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 543 - Score: 0.0 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 544 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 545 - Score: 0.0 Avg critic losses: tensor(9.4001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 546 - Score: 0.0 Avg critic losses: tensor(9.7110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 547 - Score: 0.0 Avg critic losses: tensor(8.5853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 548 - Score: 0.0 Avg critic losses: tensor(6.4269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 549 - Score: 0.0 Avg critic losses: tensor(7.1924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 550 - Score: 0.0 Avg critic losses: tensor(8.0670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 551 - Score: 0.0 Avg critic losses: tensor(7.7245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 552 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 553 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 554 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 555 - Score: 0.0 Avg critic losses: tensor(9.4202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 556 - Score: 0.0 Avg critic losses: tensor(9.1148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 557 - Score: 0.0 Avg critic losses: tensor(8.2512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 558 - Score: 0.0 Avg critic losses: tensor(7.6155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 559 - Score: 0.0 Avg critic losses: tensor(6.5703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 560 - Score: 0.0 Episode 560 - Mean score: 0.00280000004917 Avg critic losses: tensor(8.5848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 561 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 562 - Score: 0.0 Avg critic losses: tensor(6.8528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 563 - Score: 0.0 Avg critic losses: tensor(8.0176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 564 - Score: 0.0 Avg critic losses: tensor(8.5860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 565 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 566 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 567 - Score: 0.0 Avg critic losses: tensor(8.5312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 568 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 569 - Score: 0.0 Avg critic losses: tensor(9.3047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 570 - Score: 0.0 Avg critic losses: tensor(5.6679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 571 - Score: 0.0 Avg critic losses: tensor(6.7616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 572 - Score: 0.0 Avg critic losses: tensor(7.7586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 573 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0017, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 574 - Score: 0.0 Avg critic losses: tensor(8.8862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 575 - Score: 0.0 Avg critic losses: tensor(8.6555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 576 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) episode done in 12 time steps; scores: [-0.01 0. ] Episode 577 - Score: 0.0 Avg critic losses: tensor(9.4469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 578 - Score: 0.0 Avg critic losses: tensor(8.6541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 579 - Score: 0.0 Avg critic losses: tensor(7.0730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 580 - Score: 0.0 Episode 580 - Mean score: 0.00190000003204 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 581 - Score: 0.0 Avg critic losses: tensor(6.3101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 582 - Score: 0.0 Avg critic losses: tensor(9.7626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 583 - Score: 0.0 Avg critic losses: tensor(7.9237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0004, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 584 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0012, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 585 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0011, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0010, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0015, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 586 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) episode done in 12 time steps; scores: [ 0. -0.01] Episode 587 - Score: 0.0 Avg critic losses: tensor(7.6823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 588 - Score: 0.0 Avg critic losses: tensor(6.7433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 589 - Score: 0.0 Avg critic losses: tensor(8.4896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 590 - Score: 0.0 Avg critic losses: tensor(8.0059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 591 - Score: 0.0 Avg critic losses: tensor(7.5877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 592 - Score: 0.0 Avg critic losses: tensor(7.9354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 593 - Score: 0.0 Avg critic losses: tensor(8.7741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 594 - Score: 0.0 Avg critic losses: tensor(7.7575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 595 - Score: 0.0 Avg critic losses: tensor(8.8785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 596 - Score: 0.0 Avg critic losses: tensor(8.6546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 597 - Score: 0.0 Avg critic losses: tensor(7.6545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 598 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [-0.01 0. ] Episode 599 - Score: 0.0 Avg critic losses: tensor(8.3481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 600 - Score: 0.0 Episode 600 - Mean score: 0.00190000003204 Avg critic losses: tensor(7.6953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 601 - Score: 0.0 Avg critic losses: tensor(9.4486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 602 - Score: 0.0 Avg critic losses: tensor(9.0210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 603 - Score: 0.0 Avg critic losses: tensor(5.9168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 604 - Score: 0.0 Avg critic losses: tensor(7.5697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 605 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 606 - Score: 0.0 Avg critic losses: tensor(7.0028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [ 0. -0.01] Episode 607 - Score: 0.0 Avg critic losses: tensor(8.8574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 608 - Score: 0.0 Avg critic losses: tensor(9.5378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 609 - Score: 0.0 Avg critic losses: tensor(8.1149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) episode done in 16 time steps; scores: [-0.01 0. ] Episode 610 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 611 - Score: 0.0 Avg critic losses: tensor(8.1120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 612 - Score: 0.0 Avg critic losses: tensor(7.8618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 613 - Score: 0.0 Avg critic losses: tensor(7.9544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 614 - Score: 0.0 Avg critic losses: tensor(8.6765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 615 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 616 - Score: 0.0 Avg critic losses: tensor(8.7980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 617 - Score: 0.0 Avg critic losses: tensor(9.9658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 618 - Score: 0.0 Avg critic losses: tensor(7.6767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 619 - Score: 0.0900000017136 Avg critic losses: tensor(9.5398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 620 - Score: 0.0 Episode 620 - Mean score: 0.00280000004917 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 621 - Score: 0.0 Avg critic losses: tensor(8.3735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 622 - Score: 0.0 Avg critic losses: tensor(7.2036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0009, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 623 - Score: 0.0 Avg critic losses: tensor(7.8209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 624 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 625 - Score: 0.0 Avg critic losses: tensor(5.8497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 626 - Score: 0.0 Avg critic losses: tensor(6.0860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 627 - Score: 0.0 Avg critic losses: tensor(7.6054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) episode done in 25 time steps; scores: [-0.01 0. ] Episode 628 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 629 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 630 - Score: 0.0 Avg critic losses: tensor(9.0271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 631 - Score: 0.0 Avg critic losses: tensor(8.7953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 632 - Score: 0.0 Avg critic losses: tensor(5.8938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 633 - Score: 0.0 Avg critic losses: tensor(7.8462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 634 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 635 - Score: 0.0 Avg critic losses: tensor(8.1916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 636 - Score: 0.0 Avg critic losses: tensor(9.3226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 637 - Score: 0.0 Avg critic losses: tensor(7.4017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 638 - Score: 0.0 Avg critic losses: tensor(8.7841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 639 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 640 - Score: 0.0 Episode 640 - Mean score: 0.000900000017136 Avg critic losses: tensor(8.5260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 641 - Score: 0.0 Avg critic losses: tensor(7.7204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 642 - Score: 0.0 Avg critic losses: tensor(6.1163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 643 - Score: 0.0 Avg critic losses: tensor(7.7913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 644 - Score: 0.0 Avg critic losses: tensor(7.4643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 645 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 646 - Score: 0.0 Avg critic losses: tensor(6.1135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 647 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 648 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) episode done in 12 time steps; scores: [-0.01 0. ] Episode 649 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 650 - Score: 0.0 Avg critic losses: tensor(9.3301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 651 - Score: 0.0 Avg critic losses: tensor(9.6966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 652 - Score: 0.0 Avg critic losses: tensor(6.5826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 653 - Score: 0.0 Avg critic losses: tensor(9.2912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 654 - Score: 0.0 Avg critic losses: tensor(6.9859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 655 - Score: 0.0 Avg critic losses: tensor(6.3263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 656 - Score: 0.0 Avg critic losses: tensor(6.7536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) episode done in 23 time steps; scores: [-0.01 0.1 ] Episode 657 - Score: 0.10000000149 Avg critic losses: tensor(8.6416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 658 - Score: 0.0 Avg critic losses: tensor(6.7197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 659 - Score: 0.0 Avg critic losses: tensor(7.5546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 660 - Score: 0.0 Episode 660 - Mean score: 0.00190000003204 Avg critic losses: tensor(8.9831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 661 - Score: 0.0 Avg critic losses: tensor(7.2309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 662 - Score: 0.0 Avg critic losses: tensor(6.6542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 663 - Score: 0.0 Avg critic losses: tensor(6.4159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 664 - Score: 0.0 Avg critic losses: tensor(8.5453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 665 - Score: 0.0 Avg critic losses: tensor(6.3616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 666 - Score: 0.0 Avg critic losses: tensor(6.0569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 667 - Score: 0.0 Avg critic losses: tensor(7.3323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 668 - Score: 0.0 Avg critic losses: tensor(5.3533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 669 - Score: 0.0 Avg critic losses: tensor(8.9731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0006, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 670 - Score: 0.0 Avg critic losses: tensor(9.9657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 671 - Score: 0.0 Avg critic losses: tensor(8.5819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 672 - Score: 0.0 Avg critic losses: tensor(6.0926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 673 - Score: 0.0 Avg critic losses: tensor(5.4996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 674 - Score: 0.0 Avg critic losses: tensor(5.8730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 675 - Score: 0.0 Avg critic losses: tensor(7.1916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 676 - Score: 0.0 Avg critic losses: tensor(7.2578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 677 - Score: 0.0 Avg critic losses: tensor(7.5507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 678 - Score: 0.0 Avg critic losses: tensor(6.3141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0015, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 679 - Score: 0.0 Avg critic losses: tensor(7.0559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 680 - Score: 0.0 Episode 680 - Mean score: 0.00190000003204 Avg critic losses: tensor(7.0028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 681 - Score: 0.0 Avg critic losses: tensor(6.6112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 682 - Score: 0.0 Avg critic losses: tensor(8.4489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 683 - Score: 0.0 Avg critic losses: tensor(6.4002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 684 - Score: 0.0 Avg critic losses: tensor(5.7701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 685 - Score: 0.0 Avg critic losses: tensor(7.5461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 686 - Score: 0.0 Avg critic losses: tensor(5.2309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 687 - Score: 0.0 Avg critic losses: tensor(5.9113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 688 - Score: 0.0 Avg critic losses: tensor(5.9360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 689 - Score: 0.0 Avg critic losses: tensor(7.2662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 690 - Score: 0.0 Avg critic losses: tensor(7.4673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 691 - Score: 0.0 Avg critic losses: tensor(6.3131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 692 - Score: 0.0 Avg critic losses: tensor(6.9036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 693 - Score: 0.0 Avg critic losses: tensor(5.5788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 694 - Score: 0.0 Avg critic losses: tensor(5.6042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 695 - Score: 0.0 Avg critic losses: tensor(5.9288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 696 - Score: 0.0 Avg critic losses: tensor(6.6307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 697 - Score: 0.0 Avg critic losses: tensor(4.9429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 698 - Score: 0.0 Avg critic losses: tensor(6.0345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 699 - Score: 0.0 Avg critic losses: tensor(5.7528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 700 - Score: 0.0 Episode 700 - Mean score: 0.00190000003204 Avg critic losses: tensor(5.7990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 701 - Score: 0.0 Avg critic losses: tensor(5.2071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 702 - Score: 0.0 Avg critic losses: tensor(6.1578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 703 - Score: 0.0 Avg critic losses: tensor(5.4369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 704 - Score: 0.0 Avg critic losses: tensor(5.7053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 705 - Score: 0.0 Avg critic losses: tensor(5.7793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 706 - Score: 0.0 Avg critic losses: tensor(7.0552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 707 - Score: 0.0 Avg critic losses: tensor(5.6436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 708 - Score: 0.0 Avg critic losses: tensor(5.1246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 709 - Score: 0.0 Avg critic losses: tensor(4.1329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 710 - Score: 0.0 Avg critic losses: tensor(5.7776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 711 - Score: 0.0 Avg critic losses: tensor(6.2142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 712 - Score: 0.0 Avg critic losses: tensor(6.7206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 713 - Score: 0.0 Avg critic losses: tensor(8.5621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 714 - Score: 0.0 Avg critic losses: tensor(6.7034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 715 - Score: 0.0 Avg critic losses: tensor(7.5401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 716 - Score: 0.0 Avg critic losses: tensor(6.6660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 717 - Score: 0.0 Avg critic losses: tensor(6.7983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 718 - Score: 0.0 Avg critic losses: tensor(5.4351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 719 - Score: 0.0 Avg critic losses: tensor(6.2827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 720 - Score: 0.0 Episode 720 - Mean score: 0.0010000000149 Avg critic losses: tensor(6.1502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [-0.01 0. ] Episode 721 - Score: 0.0 Avg critic losses: tensor(5.0530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 722 - Score: 0.0 Avg critic losses: tensor(5.7760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 723 - Score: 0.0 Avg critic losses: tensor(6.0051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 724 - Score: 0.0 Avg critic losses: tensor(6.8246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 725 - Score: 0.0 Avg critic losses: tensor(5.8528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 726 - Score: 0.0 Avg critic losses: tensor(5.1151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 727 - Score: 0.0 Avg critic losses: tensor(8.8232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 728 - Score: 0.0 Avg critic losses: tensor(5.3172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 729 - Score: 0.0 Avg critic losses: tensor(4.4013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 730 - Score: 0.0 Avg critic losses: tensor(7.2048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 731 - Score: 0.0 Avg critic losses: tensor(5.7634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 732 - Score: 0.0 Avg critic losses: tensor(4.8589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 733 - Score: 0.0 Avg critic losses: tensor(5.3784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 734 - Score: 0.0 Avg critic losses: tensor(4.9810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 735 - Score: 0.0 Avg critic losses: tensor(5.1284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 736 - Score: 0.0 Avg critic losses: tensor(5.1695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 737 - Score: 0.0 Avg critic losses: tensor(5.1279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 738 - Score: 0.0 Avg critic losses: tensor(5.1544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 739 - Score: 0.0 Avg critic losses: tensor(4.3624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 740 - Score: 0.0 Episode 740 - Mean score: 0.0010000000149 Avg critic losses: tensor(5.4027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 741 - Score: 0.0 Avg critic losses: tensor(6.2246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 742 - Score: 0.0 Avg critic losses: tensor(8.2587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 743 - Score: 0.0 Avg critic losses: tensor(7.0614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0004, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 744 - Score: 0.0 Avg critic losses: tensor(6.5979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 745 - Score: 0.0 Avg critic losses: tensor(5.4962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 746 - Score: 0.0 Avg critic losses: tensor(6.5773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 747 - Score: 0.0 Avg critic losses: tensor(5.2904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 748 - Score: 0.0 Avg critic losses: tensor(5.4037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 749 - Score: 0.0 Avg critic losses: tensor(5.3708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 750 - Score: 0.0 Avg critic losses: tensor(6.3669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 751 - Score: 0.0 Avg critic losses: tensor(5.6958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 752 - Score: 0.0 Avg critic losses: tensor(5.7172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 753 - Score: 0.0 Avg critic losses: tensor(5.0411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 754 - Score: 0.0 Avg critic losses: tensor(4.5121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0006, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 755 - Score: 0.0 Avg critic losses: tensor(4.2538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 756 - Score: 0.0 Avg critic losses: tensor(5.3049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 757 - Score: 0.0 Avg critic losses: tensor(6.6917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.7411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 758 - Score: 0.0 Avg critic losses: tensor(6.4954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 759 - Score: 0.0 Avg critic losses: tensor(6.1352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 760 - Score: 0.0 Episode 760 - Mean score: 0.0 Avg critic losses: tensor(5.2780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.7910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 761 - Score: 0.0 Avg critic losses: tensor(4.5700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.5655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 762 - Score: 0.0 Avg critic losses: tensor(5.2317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 763 - Score: 0.0 Avg critic losses: tensor(5.8112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 764 - Score: 0.0 Avg critic losses: tensor(5.9926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 765 - Score: 0.0 Avg critic losses: tensor(5.9222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.6863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 766 - Score: 0.0 Avg critic losses: tensor(3.8608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.2132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 767 - Score: 0.0 Avg critic losses: tensor(5.2721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 768 - Score: 0.0 Avg critic losses: tensor(5.5440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 769 - Score: 0.0 Avg critic losses: tensor(8.2862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0017, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 770 - Score: 0.0 Avg critic losses: tensor(6.9982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 771 - Score: 0.0 Avg critic losses: tensor(6.9571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 772 - Score: 0.0 Avg critic losses: tensor(5.8193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 773 - Score: 0.0 Avg critic losses: tensor(4.9698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 774 - Score: 0.0 Avg critic losses: tensor(4.2238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 775 - Score: 0.0 Avg critic losses: tensor(5.6454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 776 - Score: 0.0 Avg critic losses: tensor(6.8317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 777 - Score: 0.0 Avg critic losses: tensor(6.0280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 778 - Score: 0.0 Avg critic losses: tensor(7.1525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 779 - Score: 0.0 Avg critic losses: tensor(9.5295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0003, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 780 - Score: 0.0 Episode 780 - Mean score: 0.0 Avg critic losses: tensor(9.1842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 781 - Score: 0.0 Avg critic losses: tensor(7.8475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 782 - Score: 0.0 Avg critic losses: tensor(6.8844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0015, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 783 - Score: 0.0 Avg critic losses: tensor(6.1354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 784 - Score: 0.0 Avg critic losses: tensor(6.1627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 785 - Score: 0.0 Avg critic losses: tensor(6.3521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 786 - Score: 0.0 Avg critic losses: tensor(4.9470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 787 - Score: 0.0 Avg critic losses: tensor(5.9286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 788 - Score: 0.0 Avg critic losses: tensor(5.9912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 789 - Score: 0.0 Avg critic losses: tensor(7.1589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 790 - Score: 0.0 Avg critic losses: tensor(5.7850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 791 - Score: 0.0 Avg critic losses: tensor(5.5404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 792 - Score: 0.0 Avg critic losses: tensor(5.1437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 793 - Score: 0.0 Avg critic losses: tensor(5.5059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 794 - Score: 0.0 Avg critic losses: tensor(5.2907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 795 - Score: 0.0 Avg critic losses: tensor(8.8767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 796 - Score: 0.0 Avg critic losses: tensor(7.3629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 797 - Score: 0.0 Avg critic losses: tensor(6.4361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 798 - Score: 0.0 Avg critic losses: tensor(7.1497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 799 - Score: 0.0 Avg critic losses: tensor(4.9769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 800 - Score: 0.0 Episode 800 - Mean score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 801 - Score: 0.0 Avg critic losses: tensor(6.6268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 802 - Score: 0.0 Avg critic losses: tensor(5.9587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 803 - Score: 0.0 Avg critic losses: tensor(7.3860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 804 - Score: 0.0 Avg critic losses: tensor(6.7765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 805 - Score: 0.0 Avg critic losses: tensor(8.0993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 806 - Score: 0.0 Avg critic losses: tensor(6.8986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 807 - Score: 0.0 Avg critic losses: tensor(6.5533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 808 - Score: 0.0 Avg critic losses: tensor(6.4727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 809 - Score: 0.0 Avg critic losses: tensor(7.3124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 810 - Score: 0.0 Avg critic losses: tensor(5.2548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 811 - Score: 0.0 Avg critic losses: tensor(5.7984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 812 - Score: 0.0 Avg critic losses: tensor(4.5358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 813 - Score: 0.0 Avg critic losses: tensor(6.4791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 814 - Score: 0.0 Avg critic losses: tensor(6.9669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 815 - Score: 0.0 Avg critic losses: tensor(5.7379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 816 - Score: 0.0 Avg critic losses: tensor(4.7648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 817 - Score: 0.0 Avg critic losses: tensor(6.7525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 818 - Score: 0.0 Avg critic losses: tensor(7.6933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 819 - Score: 0.0 Avg critic losses: tensor(6.6190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 820 - Score: 0.0 Episode 820 - Mean score: 0.0 Avg critic losses: tensor(7.8296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 821 - Score: 0.0 Avg critic losses: tensor(7.4977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 822 - Score: 0.0 Avg critic losses: tensor(4.8178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 823 - Score: 0.0 Avg critic losses: tensor(5.6285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) episode done in 48 time steps; scores: [-0.01 0.1 ] Episode 824 - Score: 0.10000000149 Avg critic losses: tensor(5.9839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 825 - Score: 0.0 Avg critic losses: tensor(6.4675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 826 - Score: 0.0 Avg critic losses: tensor(8.0085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 827 - Score: 0.0 Avg critic losses: tensor(8.0689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 828 - Score: 0.0 Avg critic losses: tensor(6.1971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 829 - Score: 0.0 Avg critic losses: tensor(6.3625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 830 - Score: 0.0 Avg critic losses: tensor(5.2670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 831 - Score: 0.0 Avg critic losses: tensor(6.3903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 832 - Score: 0.0 Avg critic losses: tensor(8.3524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 833 - Score: 0.0 Avg critic losses: tensor(5.7728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0015, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 834 - Score: 0.0 Avg critic losses: tensor(8.4131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0004, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0007, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 835 - Score: 0.0 Avg critic losses: tensor(5.4150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 836 - Score: 0.0 Avg critic losses: tensor(5.3028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 837 - Score: 0.0 Avg critic losses: tensor(7.5280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 838 - Score: 0.0 Avg critic losses: tensor(5.8872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 839 - Score: 0.0 Avg critic losses: tensor(6.5180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 840 - Score: 0.0 Episode 840 - Mean score: 0.0010000000149 Avg critic losses: tensor(6.9833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 841 - Score: 0.0 Avg critic losses: tensor(7.9716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 842 - Score: 0.0 Avg critic losses: tensor(5.7852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 843 - Score: 0.0 Avg critic losses: tensor(6.0705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 844 - Score: 0.0 Avg critic losses: tensor(9.9779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 845 - Score: 0.0 Avg critic losses: tensor(6.5977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 846 - Score: 0.0 Avg critic losses: tensor(4.4819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 847 - Score: 0.0 Avg critic losses: tensor(5.4863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 848 - Score: 0.0 Avg critic losses: tensor(5.8287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 849 - Score: 0.0 Avg critic losses: tensor(6.4342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 850 - Score: 0.0 Avg critic losses: tensor(5.4464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 851 - Score: 0.0 Avg critic losses: tensor(6.6247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 852 - Score: 0.0 Avg critic losses: tensor(8.7989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0017, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 853 - Score: 0.0 Avg critic losses: tensor(5.7388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 854 - Score: 0.0 Avg critic losses: tensor(6.5556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 855 - Score: 0.0 Avg critic losses: tensor(5.9575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 856 - Score: 0.0 Avg critic losses: tensor(6.1123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 857 - Score: 0.0 Avg critic losses: tensor(6.4533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 858 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0020, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 859 - Score: 0.0 Avg critic losses: tensor(8.1323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 860 - Score: 0.0 Episode 860 - Mean score: 0.0010000000149 Avg critic losses: tensor(8.0678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0015, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 861 - Score: 0.0 Avg critic losses: tensor(5.5398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 862 - Score: 0.0 Avg critic losses: tensor(8.4411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0011, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0014, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 863 - Score: 0.0 Avg critic losses: tensor(7.9047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 864 - Score: 0.0 Avg critic losses: tensor(5.5245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 865 - Score: 0.0 Avg critic losses: tensor(5.7877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0001, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 866 - Score: 0.0 Avg critic losses: tensor(8.1311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0008, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 867 - Score: 0.0 Avg critic losses: tensor(7.6517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 868 - Score: 0.0 Avg critic losses: tensor(6.0720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 869 - Score: 0.0 Avg critic losses: tensor(6.4661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 870 - Score: 0.0 Avg critic losses: tensor(6.3071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [ 0.1 -0.01] Episode 871 - Score: 0.10000000149 Avg critic losses: tensor(6.5618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 872 - Score: 0.0 Avg critic losses: tensor(6.4222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 873 - Score: 0.0 Avg critic losses: tensor(6.9131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 874 - Score: 0.0 Avg critic losses: tensor(7.1721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 875 - Score: 0.0 Avg critic losses: tensor(6.4156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0023, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 876 - Score: 0.0 Avg critic losses: tensor(7.3917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 877 - Score: 0.0 Avg critic losses: tensor(6.4855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0010, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 878 - Score: 0.0 Avg critic losses: tensor(5.7366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) episode done in 16 time steps; scores: [ 0. -0.01] Episode 879 - Score: 0.0 Avg critic losses: tensor(6.1789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 880 - Score: 0.0 Episode 880 - Mean score: 0.0020000000298 Avg critic losses: tensor(7.8082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) episode done in 12 time steps; scores: [ 0. -0.01] Episode 881 - Score: 0.0 Avg critic losses: tensor(5.0110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.6297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 882 - Score: 0.0 Avg critic losses: tensor(6.8532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 883 - Score: 0.0 Avg critic losses: tensor(5.7646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 884 - Score: 0.0 Avg critic losses: tensor(9.6213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0003, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0004, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0015, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 885 - Score: 0.0 Avg critic losses: tensor(7.6027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0023, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0008, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0010, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 886 - Score: 0.0 Avg critic losses: tensor(5.8896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0011, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 887 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0004, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 888 - Score: 0.10000000149 Avg critic losses: tensor(7.7638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0011, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0021, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 889 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0015, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0009, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 890 - Score: 0.0 Avg critic losses: tensor(7.3216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 891 - Score: 0.0 Avg critic losses: tensor(8.7632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [-0.01 0.1 ] Episode 892 - Score: 0.10000000149 Avg critic losses: tensor(5.7315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(3.6728e-05, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 893 - Score: 0.0 Avg critic losses: tensor(6.4585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 894 - Score: 0.0 Avg critic losses: tensor(8.5222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 895 - Score: 0.0 Avg critic losses: tensor(6.4841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 896 - Score: 0.0 Avg critic losses: tensor(7.1296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0017, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0005, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0006, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0012, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 897 - Score: 0.0 Avg critic losses: tensor(7.2258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 898 - Score: 0.0 Avg critic losses: tensor(4.5751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 899 - Score: 0.0 Avg critic losses: tensor(9.4538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 900 - Score: 0.0 Episode 900 - Mean score: 0.0040000000596 Avg critic losses: tensor(6.3161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [ 0.1 -0.01] Episode 901 - Score: 0.10000000149 Avg critic losses: tensor(5.3984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 902 - Score: 0.0 Avg critic losses: tensor(8.4840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 903 - Score: 0.0 Avg critic losses: tensor(8.8974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0009, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0.1 -0.01] Episode 904 - Score: 0.10000000149 Avg critic losses: tensor(7.5628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 905 - Score: 0.0 Avg critic losses: tensor(4.9989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) episode done in 27 time steps; scores: [-0.01 0.1 ] Episode 906 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 907 - Score: 0.0 Avg critic losses: tensor(7.3777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 908 - Score: 0.0 Avg critic losses: tensor(5.5191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 909 - Score: 0.0 Avg critic losses: tensor(6.2861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0010, grad_fn=<MeanBackward0>) episode done in 43 time steps; scores: [ 0.1 0.09] Episode 910 - Score: 0.10000000149 Avg critic losses: tensor(9.2911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 911 - Score: 0.0 Avg critic losses: tensor(6.6106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-7.3556e-05, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0015, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 912 - Score: 0.0 Avg critic losses: tensor(8.8483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 913 - Score: 0.0 Avg critic losses: tensor(5.0013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 914 - Score: 0.0 Avg critic losses: tensor(6.2715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 915 - Score: 0.0 Avg critic losses: tensor(7.6904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 916 - Score: 0.0 Avg critic losses: tensor(7.2457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0017, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 917 - Score: 0.0 Avg critic losses: tensor(6.4393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 918 - Score: 0.0 Avg critic losses: tensor(6.7621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 919 - Score: 0.0 Avg critic losses: tensor(8.9545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0010, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-6.8891e-05, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0005, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 920 - Score: 0.0 Episode 920 - Mean score: 0.00800000011921 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-9.0873e-05, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0023, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0004, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 921 - Score: 0.0 Avg critic losses: tensor(8.4775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 922 - Score: 0.0 Avg critic losses: tensor(5.2065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.7616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 923 - Score: 0.0 Avg critic losses: tensor(5.7022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 924 - Score: 0.0 Avg critic losses: tensor(9.7975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 925 - Score: 0.0 Avg critic losses: tensor(7.9632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 926 - Score: 0.10000000149 Avg critic losses: tensor(6.4810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 927 - Score: 0.0 Avg critic losses: tensor(7.6211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 928 - Score: 0.0 Avg critic losses: tensor(6.8717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 929 - Score: 0.0 Avg critic losses: tensor(6.3438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 930 - Score: 0.0 Avg critic losses: tensor(6.8185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 931 - Score: 0.0 Avg critic losses: tensor(9.4684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 932 - Score: 0.0 Avg critic losses: tensor(7.8047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [-0.01 0. ] Episode 933 - Score: 0.0 Avg critic losses: tensor(7.2177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 934 - Score: 0.0 Avg critic losses: tensor(8.4045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [-0.01 0. ] Episode 935 - Score: 0.0 Avg critic losses: tensor(6.4371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 936 - Score: 0.0 Avg critic losses: tensor(6.5898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 937 - Score: 0.0 Avg critic losses: tensor(8.1427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 938 - Score: 0.0 Avg critic losses: tensor(7.3828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 939 - Score: 0.10000000149 Avg critic losses: tensor(9.3877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 940 - Score: 0.0 Episode 940 - Mean score: 0.00900000013411 Avg critic losses: tensor(8.0126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 941 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 942 - Score: 0.0 Avg critic losses: tensor(7.5004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) episode done in 12 time steps; scores: [-0.01 0. ] Episode 943 - Score: 0.0 Avg critic losses: tensor(9.6675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [ 0. -0.01] Episode 944 - Score: 0.0 Avg critic losses: tensor(7.7657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 945 - Score: 0.0 Avg critic losses: tensor(7.8727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 946 - Score: 0.0 Avg critic losses: tensor(7.8562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 947 - Score: 0.0 Avg critic losses: tensor(7.6418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 948 - Score: 0.0 Avg critic losses: tensor(5.8767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 949 - Score: 0.0 Avg critic losses: tensor(8.8189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [ 0. -0.01] Episode 950 - Score: 0.0 Avg critic losses: tensor(6.6919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 951 - Score: 0.0 Avg critic losses: tensor(8.8570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 952 - Score: 0.0 Avg critic losses: tensor(7.3178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 953 - Score: 0.10000000149 Avg critic losses: tensor(8.1332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 954 - Score: 0.0 Avg critic losses: tensor(8.0002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 955 - Score: 0.0 Avg critic losses: tensor(6.9782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 956 - Score: 0.0 Avg critic losses: tensor(9.3091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 957 - Score: 0.0 Avg critic losses: tensor(7.1038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 958 - Score: 0.0 Avg critic losses: tensor(7.9142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [ 0. -0.01] Episode 959 - Score: 0.0 Avg critic losses: tensor(8.2010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 960 - Score: 0.0 Episode 960 - Mean score: 0.010000000149 Avg critic losses: tensor(8.1011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 961 - Score: 0.0 Avg critic losses: tensor(7.0052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 962 - Score: 0.0 Avg critic losses: tensor(6.3068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 963 - Score: 0.0 Avg critic losses: tensor(7.3199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 964 - Score: 0.0 Avg critic losses: tensor(7.0796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 965 - Score: 0.0 Avg critic losses: tensor(6.0303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 966 - Score: 0.0 Avg critic losses: tensor(6.6881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 967 - Score: 0.0 Avg critic losses: tensor(7.4557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [-0.01 0. ] Episode 968 - Score: 0.0 Avg critic losses: tensor(5.9562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 969 - Score: 0.0 Avg critic losses: tensor(8.5670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 970 - Score: 0.0 Avg critic losses: tensor(5.9192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 971 - Score: 0.0 Avg critic losses: tensor(7.2447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 972 - Score: 0.0 Avg critic losses: tensor(7.0793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 973 - Score: 0.0 Avg critic losses: tensor(7.8730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 974 - Score: 0.0 Avg critic losses: tensor(7.2197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [-0.01 0. ] Episode 975 - Score: 0.0 Avg critic losses: tensor(6.1750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0023, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 976 - Score: 0.0 Avg critic losses: tensor(6.8583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 977 - Score: 0.0 Avg critic losses: tensor(6.3281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 978 - Score: 0.0 Avg critic losses: tensor(7.2931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 979 - Score: 0.0 Avg critic losses: tensor(5.3857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 980 - Score: 0.0 Episode 980 - Mean score: 0.00900000013411 Avg critic losses: tensor(6.4491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 981 - Score: 0.0 Avg critic losses: tensor(9.2314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 982 - Score: 0.0 Avg critic losses: tensor(8.1963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 983 - Score: 0.0 Avg critic losses: tensor(5.9438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 984 - Score: 0.0 Avg critic losses: tensor(7.7469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 985 - Score: 0.0 Avg critic losses: tensor(7.4058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 986 - Score: 0.0 Avg critic losses: tensor(9.6865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 987 - Score: 0.0 Avg critic losses: tensor(8.8123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 988 - Score: 0.0 Avg critic losses: tensor(6.8532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 989 - Score: 0.0 Avg critic losses: tensor(6.7795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 990 - Score: 0.0 Avg critic losses: tensor(6.9042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [-0.01 0. ] Episode 991 - Score: 0.0 Avg critic losses: tensor(7.8086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [-0.01 0. ] Episode 992 - Score: 0.0 Avg critic losses: tensor(8.9303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 993 - Score: 0.0 Avg critic losses: tensor(7.7988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 994 - Score: 0.0 Avg critic losses: tensor(5.4532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 995 - Score: 0.0 Avg critic losses: tensor(6.0797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 996 - Score: 0.0 Avg critic losses: tensor(6.1350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [ 0. -0.01] Episode 997 - Score: 0.0 Avg critic losses: tensor(5.6789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 998 - Score: 0.0 Avg critic losses: tensor(6.7802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 999 - Score: 0.0 Avg critic losses: tensor(7.1804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [ 0. -0.01] Episode 1000 - Score: 0.0 Episode 1000 - Mean score: 0.00700000010431 Avg critic losses: tensor(5.9966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1001 - Score: 0.0 Avg critic losses: tensor(8.5176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1002 - Score: 0.0 Avg critic losses: tensor(6.4817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1003 - Score: 0.0 Avg critic losses: tensor(6.7128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) episode done in 16 time steps; scores: [ 0. -0.01] Episode 1004 - Score: 0.0 Avg critic losses: tensor(5.0026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1005 - Score: 0.0 Avg critic losses: tensor(5.5158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1006 - Score: 0.0 Avg critic losses: tensor(5.2289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1007 - Score: 0.0 Avg critic losses: tensor(6.9164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1008 - Score: 0.0 Avg critic losses: tensor(7.7888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0017, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1009 - Score: 0.0 Avg critic losses: tensor(7.0350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1010 - Score: 0.0 Avg critic losses: tensor(5.5314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1011 - Score: 0.0 Avg critic losses: tensor(5.1943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1012 - Score: 0.0 Avg critic losses: tensor(6.3348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) episode done in 12 time steps; scores: [-0.01 0. ] Episode 1013 - Score: 0.0 Avg critic losses: tensor(7.8011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1014 - Score: 0.0 Avg critic losses: tensor(5.5082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1015 - Score: 0.0 Avg critic losses: tensor(8.9132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1016 - Score: 0.0 Avg critic losses: tensor(6.4972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1017 - Score: 0.0 Avg critic losses: tensor(6.3175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1018 - Score: 0.0 Avg critic losses: tensor(9.4135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1019 - Score: 0.0 Avg critic losses: tensor(5.6409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1020 - Score: 0.0 Episode 1020 - Mean score: 0.0030000000447 Avg critic losses: tensor(7.6218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1021 - Score: 0.0 Avg critic losses: tensor(7.2088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1022 - Score: 0.0 Avg critic losses: tensor(6.0484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0002, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1023 - Score: 0.0 Avg critic losses: tensor(7.9558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0003, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0017, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0011, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1024 - Score: 0.0 Avg critic losses: tensor(7.0002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1025 - Score: 0.0 Avg critic losses: tensor(7.1510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1026 - Score: 0.0 Avg critic losses: tensor(7.0926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1027 - Score: 0.0 Avg critic losses: tensor(6.9065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1028 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1029 - Score: 0.10000000149 Avg critic losses: tensor(9.4456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1030 - Score: 0.0 Avg critic losses: tensor(7.1020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1031 - Score: 0.0 Avg critic losses: tensor(5.5688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1032 - Score: 0.0 Avg critic losses: tensor(6.8964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1033 - Score: 0.0 Avg critic losses: tensor(8.4051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1034 - Score: 0.0 Avg critic losses: tensor(5.9152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1035 - Score: 0.0 Avg critic losses: tensor(5.4805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1036 - Score: 0.0 Avg critic losses: tensor(8.8040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1037 - Score: 0.0 Avg critic losses: tensor(6.7083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1038 - Score: 0.0 Avg critic losses: tensor(5.9452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1039 - Score: 0.0 Avg critic losses: tensor(9.4590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1040 - Score: 0.0 Episode 1040 - Mean score: 0.00290000004694 Avg critic losses: tensor(5.5559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1041 - Score: 0.0 Avg critic losses: tensor(9.1283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1042 - Score: 0.0 Avg critic losses: tensor(6.1269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1043 - Score: 0.0 Avg critic losses: tensor(8.3358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1044 - Score: 0.0 Avg critic losses: tensor(6.0394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1045 - Score: 0.0 Avg critic losses: tensor(7.8935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1046 - Score: 0.0 Avg critic losses: tensor(8.9995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1047 - Score: 0.0 Avg critic losses: tensor(7.4173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1048 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0002, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0007, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) episode done in 12 time steps; scores: [-0.01 0. ] Episode 1049 - Score: 0.0 Avg critic losses: tensor(9.1506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1050 - Score: 0.0 Avg critic losses: tensor(6.9079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1051 - Score: 0.0 Avg critic losses: tensor(6.5208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) episode done in 34 time steps; scores: [-0.01 0.1 ] Episode 1052 - Score: 0.10000000149 Avg critic losses: tensor(6.5758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1053 - Score: 0.0 Avg critic losses: tensor(7.4064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1054 - Score: 0.0 Avg critic losses: tensor(9.7235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1055 - Score: 0.0 Avg critic losses: tensor(9.0298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [-0.01 0. ] Episode 1056 - Score: 0.0 Avg critic losses: tensor(7.4008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1057 - Score: 0.0 Avg critic losses: tensor(6.2899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1058 - Score: 0.0 Avg critic losses: tensor(7.0287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1059 - Score: 0.0 Avg critic losses: tensor(8.6376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1060 - Score: 0.0 Episode 1060 - Mean score: 0.00290000004694 Avg critic losses: tensor(7.1372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) episode done in 21 time steps; scores: [-0.01 0. ] Episode 1061 - Score: 0.0 Avg critic losses: tensor(6.8500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1062 - Score: 0.0 Avg critic losses: tensor(9.8876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1063 - Score: 0.0 Avg critic losses: tensor(7.5518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1064 - Score: 0.0 Avg critic losses: tensor(7.9799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) episode done in 12 time steps; scores: [-0.01 0. ] Episode 1065 - Score: 0.0 Avg critic losses: tensor(9.2734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1066 - Score: 0.0 Avg critic losses: tensor(6.8906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1067 - Score: 0.0 Avg critic losses: tensor(8.0809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0010, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1068 - Score: 0.0 Avg critic losses: tensor(9.6210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0004, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1069 - Score: 0.0 Avg critic losses: tensor(6.6694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) episode done in 12 time steps; scores: [-0.01 0. ] Episode 1070 - Score: 0.0 Avg critic losses: tensor(7.7199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1071 - Score: 0.0 Avg critic losses: tensor(6.1044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1072 - Score: 0.0 Avg critic losses: tensor(5.4625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1073 - Score: 0.0 Avg critic losses: tensor(5.7659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1074 - Score: 0.0 Avg critic losses: tensor(6.9691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1075 - Score: 0.0 Avg critic losses: tensor(5.9970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1076 - Score: 0.0 Avg critic losses: tensor(6.0747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1077 - Score: 0.0 Avg critic losses: tensor(7.6447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1078 - Score: 0.0 Avg critic losses: tensor(7.5183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1079 - Score: 0.0 Avg critic losses: tensor(5.5443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1080 - Score: 0.0 Episode 1080 - Mean score: 0.00290000004694 Avg critic losses: tensor(5.6183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1081 - Score: 0.0 Avg critic losses: tensor(7.8141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1082 - Score: 0.0 Avg critic losses: tensor(7.0008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1083 - Score: 0.0 Avg critic losses: tensor(9.4576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1084 - Score: 0.0 Avg critic losses: tensor(7.4865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0006, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0003, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0003, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1085 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1086 - Score: 0.0 Avg critic losses: tensor(5.7308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1087 - Score: 0.0 Avg critic losses: tensor(8.2945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1088 - Score: 0.0 Avg critic losses: tensor(6.2233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0023, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1089 - Score: 0.0 Avg critic losses: tensor(5.1769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1090 - Score: 0.0 Avg critic losses: tensor(6.3412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1091 - Score: 0.0 Avg critic losses: tensor(5.3949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1092 - Score: 0.0 Avg critic losses: tensor(6.5603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1093 - Score: 0.0 Avg critic losses: tensor(6.7336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1094 - Score: 0.0 Avg critic losses: tensor(7.4020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0012, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1095 - Score: 0.0 Avg critic losses: tensor(8.8561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1096 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1097 - Score: 0.0 Avg critic losses: tensor(7.9885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0008, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) episode done in 12 time steps; scores: [-0.01 0. ] Episode 1098 - Score: 0.0 Avg critic losses: tensor(9.1628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1099 - Score: 0.0 Avg critic losses: tensor(6.0376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1100 - Score: 0.0 Episode 1100 - Mean score: 0.00290000004694 Avg critic losses: tensor(7.3243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [ 0. -0.01] Episode 1101 - Score: 0.0 Avg critic losses: tensor(5.7914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1102 - Score: 0.0 Avg critic losses: tensor(7.2960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0023, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1103 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1104 - Score: 0.0 Avg critic losses: tensor(6.7100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0007, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0005, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0008, grad_fn=<MeanBackward0>) episode done in 12 time steps; scores: [-0.01 0. ] Episode 1105 - Score: 0.0 Avg critic losses: tensor(7.8964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0009, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0007, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1106 - Score: 0.0 Avg critic losses: tensor(5.6283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) episode done in 12 time steps; scores: [ 0. -0.01] Episode 1107 - Score: 0.0 Avg critic losses: tensor(7.5044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1108 - Score: 0.0 Avg critic losses: tensor(6.7947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0004, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1109 - Score: 0.0 Avg critic losses: tensor(5.6251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1110 - Score: 0.0 Avg critic losses: tensor(7.3685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1111 - Score: 0.0 Avg critic losses: tensor(6.9775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) episode done in 40 time steps; scores: [-0.01 0.1 ] Episode 1112 - Score: 0.10000000149 Avg critic losses: tensor(6.0730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1113 - Score: 0.0 Avg critic losses: tensor(6.3077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1114 - Score: 0.0 Avg critic losses: tensor(6.9985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1115 - Score: 0.0 Avg critic losses: tensor(7.6593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0007, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1116 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1117 - Score: 0.0 Avg critic losses: tensor(8.0912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1118 - Score: 0.0 Avg critic losses: tensor(6.8912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1119 - Score: 0.0 Avg critic losses: tensor(6.8668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) episode done in 16 time steps; scores: [ 0. -0.01] Episode 1120 - Score: 0.0 Episode 1120 - Mean score: 0.00390000006184 Avg critic losses: tensor(7.9964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1121 - Score: 0.0 Avg critic losses: tensor(7.7723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0009, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) episode done in 43 time steps; scores: [ 0.1 -0.01] Episode 1122 - Score: 0.10000000149 Avg critic losses: tensor(7.7175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1123 - Score: 0.0 Avg critic losses: tensor(7.8635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1124 - Score: 0.0 Avg critic losses: tensor(6.7727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1125 - Score: 0.0 Avg critic losses: tensor(8.9576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0017, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0017, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1126 - Score: 0.0 Avg critic losses: tensor(7.9235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1127 - Score: 0.0 Avg critic losses: tensor(5.8517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1128 - Score: 0.0 Avg critic losses: tensor(8.7978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0008, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1129 - Score: 0.0 Avg critic losses: tensor(8.2853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1130 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-6.9566e-05, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0005, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1131 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1132 - Score: 0.0 Avg critic losses: tensor(4.8885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0005, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1133 - Score: 0.0 Avg critic losses: tensor(6.6284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(9.4037e-05, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0004, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1134 - Score: 0.0 Avg critic losses: tensor(6.0293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1135 - Score: 0.0 Avg critic losses: tensor(7.7135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1136 - Score: 0.0 Avg critic losses: tensor(5.6496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0010, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1137 - Score: 0.0 Avg critic losses: tensor(6.7502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1138 - Score: 0.0 Avg critic losses: tensor(9.7658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1139 - Score: 0.0 Avg critic losses: tensor(7.3194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0008, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 0.09] Episode 1140 - Score: 0.10000000149 Episode 1140 - Mean score: 0.00500000007451 Avg critic losses: tensor(6.0620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0008, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0009, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1141 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 1142 - Score: 0.10000000149 Avg critic losses: tensor(6.5676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1143 - Score: 0.0 Avg critic losses: tensor(8.2844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1144 - Score: 0.0 Avg critic losses: tensor(8.2295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1145 - Score: 0.0 Avg critic losses: tensor(5.5089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1146 - Score: 0.0 Avg critic losses: tensor(6.3930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(4.7697e-05, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0015, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1147 - Score: 0.0 Avg critic losses: tensor(7.3487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1148 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1149 - Score: 0.0 Avg critic losses: tensor(6.3378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1150 - Score: 0.0 Avg critic losses: tensor(8.5482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1151 - Score: 0.0 Avg critic losses: tensor(7.0591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1152 - Score: 0.0 Avg critic losses: tensor(9.0838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1153 - Score: 0.0 Avg critic losses: tensor(6.9137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1154 - Score: 0.10000000149 Avg critic losses: tensor(8.6388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1155 - Score: 0.0 Avg critic losses: tensor(8.1682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0016, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 1156 - Score: 0.10000000149 Avg critic losses: tensor(8.5596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1157 - Score: 0.0 Avg critic losses: tensor(8.2753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1158 - Score: 0.0 Avg critic losses: tensor(9.0500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1159 - Score: 0.10000000149 Avg critic losses: tensor(8.9749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1160 - Score: 0.0 Episode 1160 - Mean score: 0.00800000011921 Avg critic losses: tensor(7.8854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1161 - Score: 0.0 Avg critic losses: tensor(8.0501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1162 - Score: 0.0 Avg critic losses: tensor(6.3585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1163 - Score: 0.10000000149 Avg critic losses: tensor(7.5699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1164 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1165 - Score: 0.0 Avg critic losses: tensor(7.2844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0012, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1166 - Score: 0.0 Avg critic losses: tensor(5.1868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1167 - Score: 0.0 Avg critic losses: tensor(9.7224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1168 - Score: 0.0 Avg critic losses: tensor(6.9633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1169 - Score: 0.0 Avg critic losses: tensor(8.9138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0012, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0007, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1170 - Score: 0.0 Avg critic losses: tensor(5.1873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0002, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1171 - Score: 0.0 Avg critic losses: tensor(5.7121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0010, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0009, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1172 - Score: 0.0 Avg critic losses: tensor(9.4054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0009, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1173 - Score: 0.0 Avg critic losses: tensor(6.8043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0010, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0015, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [ 0. -0.01] Episode 1174 - Score: 0.0 Avg critic losses: tensor(6.0239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1175 - Score: 0.0 Avg critic losses: tensor(6.1947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1176 - Score: 0.0 Avg critic losses: tensor(6.8720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1177 - Score: 0.0 Avg critic losses: tensor(7.9144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1178 - Score: 0.0 Avg critic losses: tensor(8.1785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1179 - Score: 0.0 Avg critic losses: tensor(7.2351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0010, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1180 - Score: 0.0 Episode 1180 - Mean score: 0.00900000013411 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [-0.01 0. ] Episode 1181 - Score: 0.0 Avg critic losses: tensor(7.7000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0010, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1182 - Score: 0.0 Avg critic losses: tensor(8.0526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1183 - Score: 0.0 Avg critic losses: tensor(8.4792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1184 - Score: 0.0 Avg critic losses: tensor(7.3165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1185 - Score: 0.0 Avg critic losses: tensor(9.5549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1186 - Score: 0.0 Avg critic losses: tensor(8.5847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1187 - Score: 0.0 Avg critic losses: tensor(5.4921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1188 - Score: 0.0 Avg critic losses: tensor(6.1333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-5.8815e-05, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1189 - Score: 0.0 Avg critic losses: tensor(8.0466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1190 - Score: 0.0 Avg critic losses: tensor(6.6474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1191 - Score: 0.0 Avg critic losses: tensor(7.0895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1192 - Score: 0.0 Avg critic losses: tensor(8.2465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0023, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1193 - Score: 0.0 Avg critic losses: tensor(7.3120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [ 0. 0.09] Episode 1194 - Score: 0.0900000017136 Avg critic losses: tensor(6.4733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1195 - Score: 0.0 Avg critic losses: tensor(9.0064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0023, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1196 - Score: 0.0 Avg critic losses: tensor(5.5445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1197 - Score: 0.0 Avg critic losses: tensor(8.2001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0023, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0005, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1198 - Score: 0.0 Avg critic losses: tensor(5.4113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0010, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0023, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0015, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 1199 - Score: 0.10000000149 Avg critic losses: tensor(7.1996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1200 - Score: 0.0900000017136 Episode 1200 - Mean score: 0.0118000001833 Avg critic losses: tensor(8.8940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0015, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0020, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1201 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1202 - Score: 0.0900000017136 Avg critic losses: tensor(6.7940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0.1 -0.01] Episode 1203 - Score: 0.10000000149 Avg critic losses: tensor(6.8013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1204 - Score: 0.0 Avg critic losses: tensor(5.8265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1205 - Score: 0.0 Avg critic losses: tensor(6.3863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1206 - Score: 0.0 Avg critic losses: tensor(5.6274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0005, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.09 0.2 ] Episode 1207 - Score: 0.20000000298 Avg critic losses: tensor(7.2705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1208 - Score: 0.0 Avg critic losses: tensor(7.6969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1209 - Score: 0.0 Avg critic losses: tensor(7.4499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1210 - Score: 0.0 Avg critic losses: tensor(7.4183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1211 - Score: 0.0 Avg critic losses: tensor(6.6897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1212 - Score: 0.10000000149 Avg critic losses: tensor(6.9961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1213 - Score: 0.0 Avg critic losses: tensor(7.5060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1214 - Score: 0.0 Avg critic losses: tensor(5.9655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1215 - Score: 0.0 Avg critic losses: tensor(5.5021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) episode done in 32 time steps; scores: [-0.01 0.1 ] Episode 1216 - Score: 0.10000000149 Avg critic losses: tensor(6.4130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1217 - Score: 0.10000000149 Avg critic losses: tensor(5.7171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1218 - Score: 0.0 Avg critic losses: tensor(8.1718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1219 - Score: 0.0 Avg critic losses: tensor(5.1844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1220 - Score: 0.0 Episode 1220 - Mean score: 0.0186000002921 Avg critic losses: tensor(7.4564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1221 - Score: 0.0 Avg critic losses: tensor(8.5011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1222 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1223 - Score: 0.0 Avg critic losses: tensor(7.1255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1224 - Score: 0.0 Avg critic losses: tensor(6.7414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [-0.01 0. ] Episode 1225 - Score: 0.0 Avg critic losses: tensor(9.0634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1226 - Score: 0.0 Avg critic losses: tensor(8.2601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1227 - Score: 0.0 Avg critic losses: tensor(8.0000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1228 - Score: 0.0 Avg critic losses: tensor(6.2865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0015, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1229 - Score: 0.0 Avg critic losses: tensor(6.6977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0013, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1230 - Score: 0.0 Avg critic losses: tensor(8.2611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1231 - Score: 0.0 Avg critic losses: tensor(8.5330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) episode done in 16 time steps; scores: [ 0. -0.01] Episode 1232 - Score: 0.0 Avg critic losses: tensor(9.6570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) episode done in 43 time steps; scores: [ 0.1 -0.01] Episode 1233 - Score: 0.10000000149 Avg critic losses: tensor(6.3359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1234 - Score: 0.0 Avg critic losses: tensor(6.7785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1235 - Score: 0.0 Avg critic losses: tensor(6.5607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) episode done in 19 time steps; scores: [-0.01 0. ] Episode 1236 - Score: 0.0 Avg critic losses: tensor(7.6551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1237 - Score: 0.0 Avg critic losses: tensor(6.1286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0017, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0003, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1238 - Score: 0.0 Avg critic losses: tensor(6.1835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1239 - Score: 0.10000000149 Avg critic losses: tensor(7.6479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1240 - Score: 0.0 Episode 1240 - Mean score: 0.0185000002943 Avg critic losses: tensor(7.7408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [-0.01 0.1 ] Episode 1241 - Score: 0.10000000149 Avg critic losses: tensor(6.6365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1242 - Score: 0.0 Avg critic losses: tensor(7.9206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1243 - Score: 0.0 Avg critic losses: tensor(5.8505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1244 - Score: 0.0 Avg critic losses: tensor(6.6975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1245 - Score: 0.0 Avg critic losses: tensor(5.7922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1246 - Score: 0.0 Avg critic losses: tensor(7.9473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [-0.01 0.1 ] Episode 1247 - Score: 0.10000000149 Avg critic losses: tensor(6.5764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [-0.01 0. ] Episode 1248 - Score: 0.0 Avg critic losses: tensor(8.2786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1249 - Score: 0.0 Avg critic losses: tensor(8.2911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1250 - Score: 0.0 Avg critic losses: tensor(5.4119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1251 - Score: 0.0 Avg critic losses: tensor(7.4427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1252 - Score: 0.0900000017136 Avg critic losses: tensor(6.6668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1253 - Score: 0.0 Avg critic losses: tensor(9.0766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1254 - Score: 0.10000000149 Avg critic losses: tensor(7.0311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1255 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1256 - Score: 0.0 Avg critic losses: tensor(7.6465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1257 - Score: 0.0 Avg critic losses: tensor(7.3530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0. 0.09] Episode 1258 - Score: 0.0900000017136 Avg critic losses: tensor(7.2712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1259 - Score: 0.10000000149 Avg critic losses: tensor(8.5746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1260 - Score: 0.0900000017136 Episode 1260 - Mean score: 0.0212000003457 Avg critic losses: tensor(9.4475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1261 - Score: 0.0 Avg critic losses: tensor(4.8390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) episode done in 18 time steps; scores: [ 0.1 -0.01] Episode 1262 - Score: 0.10000000149 Avg critic losses: tensor(5.7472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0012, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1263 - Score: 0.10000000149 Avg critic losses: tensor(8.9129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1264 - Score: 0.10000000149 Avg critic losses: tensor(6.0402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1265 - Score: 0.0 Avg critic losses: tensor(6.9726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0. 0.09] Episode 1266 - Score: 0.0900000017136 Avg critic losses: tensor(6.7877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1267 - Score: 0.0900000017136 Avg critic losses: tensor(6.0568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) episode done in 12 time steps; scores: [ 0. -0.01] Episode 1268 - Score: 0.0 Avg critic losses: tensor(6.8149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1269 - Score: 0.0900000017136 Avg critic losses: tensor(6.9537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0020, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1270 - Score: 0.0 Avg critic losses: tensor(7.8924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1271 - Score: 0.10000000149 Avg critic losses: tensor(6.8496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1272 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0011, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1273 - Score: 0.10000000149 Avg critic losses: tensor(6.1137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1274 - Score: 0.10000000149 Avg critic losses: tensor(5.3051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1275 - Score: 0.10000000149 Avg critic losses: tensor(6.4903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1276 - Score: 0.10000000149 Avg critic losses: tensor(5.6081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1277 - Score: 0.10000000149 Avg critic losses: tensor(5.9107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1278 - Score: 0.0900000017136 Avg critic losses: tensor(8.8204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1279 - Score: 0.0 Avg critic losses: tensor(6.5132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1280 - Score: 0.0 Episode 1280 - Mean score: 0.0338000005484 Avg critic losses: tensor(8.5804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1281 - Score: 0.10000000149 Avg critic losses: tensor(6.9985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0017, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0008, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1282 - Score: 0.0900000017136 Avg critic losses: tensor(6.7279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1283 - Score: 0.10000000149 Avg critic losses: tensor(6.0989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1284 - Score: 0.0 Avg critic losses: tensor(6.7726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1285 - Score: 0.0 Avg critic losses: tensor(9.1890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0023, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1286 - Score: 0.0 Avg critic losses: tensor(6.6514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0002, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0006, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1287 - Score: 0.0 Avg critic losses: tensor(7.4332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1288 - Score: 0.10000000149 Avg critic losses: tensor(6.2297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0022, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1289 - Score: 0.0 Avg critic losses: tensor(8.6936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1290 - Score: 0.0900000017136 Avg critic losses: tensor(6.6263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1291 - Score: 0.0 Avg critic losses: tensor(6.9700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1292 - Score: 0.0 Avg critic losses: tensor(6.0191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1293 - Score: 0.0 Avg critic losses: tensor(6.0746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1294 - Score: 0.0 Avg critic losses: tensor(6.4461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0006, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0001, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1295 - Score: 0.0900000017136 Avg critic losses: tensor(6.1201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1296 - Score: 0.0 Avg critic losses: tensor(6.3423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1297 - Score: 0.0 Avg critic losses: tensor(9.1444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0008, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1298 - Score: 0.10000000149 Avg critic losses: tensor(8.0945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1299 - Score: 0.0 Avg critic losses: tensor(5.7094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0011, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1300 - Score: 0.0900000017136 Episode 1300 - Mean score: 0.0386000006273 Avg critic losses: tensor(7.8509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0006, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0006, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1301 - Score: 0.0 Avg critic losses: tensor(6.9662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0007, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0015, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1302 - Score: 0.10000000149 Avg critic losses: tensor(7.9852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0015, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1303 - Score: 0.0900000017136 Avg critic losses: tensor(9.0945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1304 - Score: 0.10000000149 Avg critic losses: tensor(7.0810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0001, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1305 - Score: 0.0 Avg critic losses: tensor(6.4289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0019, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1306 - Score: 0.0 Avg critic losses: tensor(8.0479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0033, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1307 - Score: 0.0900000017136 Avg critic losses: tensor(7.9032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1308 - Score: 0.0 Avg critic losses: tensor(6.6974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1309 - Score: 0.0900000017136 Avg critic losses: tensor(9.2074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1310 - Score: 0.10000000149 Avg critic losses: tensor(7.3766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1311 - Score: 0.0 Avg critic losses: tensor(7.2830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1312 - Score: 0.10000000149 Avg critic losses: tensor(7.5556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1313 - Score: 0.0 Avg critic losses: tensor(5.4996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1314 - Score: 0.0 Avg critic losses: tensor(7.0330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1315 - Score: 0.0 Avg critic losses: tensor(5.1948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1316 - Score: 0.0 Avg critic losses: tensor(9.8419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0010, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) episode done in 12 time steps; scores: [-0.01 0. ] Episode 1317 - Score: 0.0 Avg critic losses: tensor(6.9292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1318 - Score: 0.0 Avg critic losses: tensor(5.5506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1319 - Score: 0.0900000017136 Avg critic losses: tensor(5.6314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1320 - Score: 0.0 Episode 1320 - Mean score: 0.0384000006318 Avg critic losses: tensor(5.6012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1321 - Score: 0.0900000017136 Avg critic losses: tensor(5.5859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [ 0. 0.09] Episode 1322 - Score: 0.0900000017136 Avg critic losses: tensor(7.5954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1323 - Score: 0.0 Avg critic losses: tensor(6.8624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1324 - Score: 0.10000000149 Avg critic losses: tensor(5.9691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1325 - Score: 0.0 Avg critic losses: tensor(6.3440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1326 - Score: 0.10000000149 Avg critic losses: tensor(7.6294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1327 - Score: 0.0 Avg critic losses: tensor(7.2745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1328 - Score: 0.10000000149 Avg critic losses: tensor(8.8294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1329 - Score: 0.0 Avg critic losses: tensor(7.5895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1330 - Score: 0.0 Avg critic losses: tensor(5.1939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1331 - Score: 0.10000000149 Avg critic losses: tensor(5.2784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1332 - Score: 0.10000000149 Avg critic losses: tensor(5.0691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1333 - Score: 0.0900000017136 Avg critic losses: tensor(5.4114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1334 - Score: 0.0 Avg critic losses: tensor(7.1626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1335 - Score: 0.10000000149 Avg critic losses: tensor(6.1196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1336 - Score: 0.0900000017136 Avg critic losses: tensor(6.3579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0005, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0012, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1337 - Score: 0.0 Avg critic losses: tensor(7.4122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1338 - Score: 0.10000000149 Avg critic losses: tensor(8.0778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0026, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0017, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1339 - Score: 0.10000000149 Avg critic losses: tensor(5.8208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0. 0.09] Episode 1340 - Score: 0.0900000017136 Episode 1340 - Mean score: 0.0480000007898 Avg critic losses: tensor(6.0543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.7460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1341 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1342 - Score: 0.0 Avg critic losses: tensor(5.3543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0. 0.09] Episode 1343 - Score: 0.0900000017136 Avg critic losses: tensor(7.9393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1344 - Score: 0.0 Avg critic losses: tensor(5.7621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1345 - Score: 0.0900000017136 Avg critic losses: tensor(8.8160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1346 - Score: 0.0 Avg critic losses: tensor(6.6495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1347 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1348 - Score: 0.0 Avg critic losses: tensor(6.4488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1349 - Score: 0.0 Avg critic losses: tensor(4.7964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1350 - Score: 0.0 Avg critic losses: tensor(6.1175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1351 - Score: 0.0 Avg critic losses: tensor(6.7960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1352 - Score: 0.0 Avg critic losses: tensor(5.2431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1353 - Score: 0.0 Avg critic losses: tensor(7.4151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1354 - Score: 0.10000000149 Avg critic losses: tensor(6.2834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1355 - Score: 0.0 Avg critic losses: tensor(8.4093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1356 - Score: 0.0 Avg critic losses: tensor(7.9043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1357 - Score: 0.0900000017136 Avg critic losses: tensor(6.1409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) episode done in 27 time steps; scores: [ 0. -0.01] Episode 1358 - Score: 0.0 Avg critic losses: tensor(8.1828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 1359 - Score: 0.10000000149 Avg critic losses: tensor(5.9292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [ 0.1 -0.01] Episode 1360 - Score: 0.10000000149 Episode 1360 - Mean score: 0.0488000008091 Avg critic losses: tensor(8.2027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1361 - Score: 0.0 Avg critic losses: tensor(6.0241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1362 - Score: 0.0 Avg critic losses: tensor(7.9763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1363 - Score: 0.0 Avg critic losses: tensor(7.0540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1364 - Score: 0.0 Avg critic losses: tensor(5.1524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1365 - Score: 0.10000000149 Avg critic losses: tensor(8.3292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1366 - Score: 0.0 Avg critic losses: tensor(5.9157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1367 - Score: 0.0 Avg critic losses: tensor(4.5667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1368 - Score: 0.0 Avg critic losses: tensor(7.5632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1369 - Score: 0.0 Avg critic losses: tensor(7.1146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1370 - Score: 0.0 Avg critic losses: tensor(4.8823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1371 - Score: 0.0 Avg critic losses: tensor(5.7814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1372 - Score: 0.0 Avg critic losses: tensor(8.6477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1373 - Score: 0.0 Avg critic losses: tensor(8.7453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1374 - Score: 0.0900000017136 Avg critic losses: tensor(6.6906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1375 - Score: 0.0 Avg critic losses: tensor(7.5169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1376 - Score: 0.0 Avg critic losses: tensor(5.3678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1377 - Score: 0.0 Avg critic losses: tensor(9.1737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1378 - Score: 0.0 Avg critic losses: tensor(6.4772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1379 - Score: 0.10000000149 Avg critic losses: tensor(4.8099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1380 - Score: 0.0 Episode 1380 - Mean score: 0.0381000006385 Avg critic losses: tensor(5.6618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1381 - Score: 0.0 Avg critic losses: tensor(5.0738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1382 - Score: 0.0 Avg critic losses: tensor(7.3635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1383 - Score: 0.0 Avg critic losses: tensor(6.9723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1384 - Score: 0.0 Avg critic losses: tensor(6.0048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1385 - Score: 0.0 Avg critic losses: tensor(6.3682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1386 - Score: 0.0 Avg critic losses: tensor(7.7608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1387 - Score: 0.0 Avg critic losses: tensor(6.6585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1388 - Score: 0.0 Avg critic losses: tensor(5.6883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1389 - Score: 0.10000000149 Avg critic losses: tensor(6.2367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1390 - Score: 0.0 Avg critic losses: tensor(6.4408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1391 - Score: 0.0 Avg critic losses: tensor(7.5486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [-0.01 0. ] Episode 1392 - Score: 0.0 Avg critic losses: tensor(6.7982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1393 - Score: 0.0 Avg critic losses: tensor(5.0494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1394 - Score: 0.0 Avg critic losses: tensor(8.2241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1395 - Score: 0.0 Avg critic losses: tensor(6.9919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1396 - Score: 0.0 Avg critic losses: tensor(9.0714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0028, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1397 - Score: 0.0 Avg critic losses: tensor(9.0307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1398 - Score: 0.0 Avg critic losses: tensor(4.4686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1399 - Score: 0.10000000149 Avg critic losses: tensor(5.1168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1400 - Score: 0.0900000017136 Episode 1400 - Mean score: 0.0334000005573 Avg critic losses: tensor(5.6152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1401 - Score: 0.0 Avg critic losses: tensor(6.6183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1402 - Score: 0.0 Avg critic losses: tensor(6.6908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1403 - Score: 0.0 Avg critic losses: tensor(6.9004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1404 - Score: 0.0900000017136 Avg critic losses: tensor(7.6185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1405 - Score: 0.0 Avg critic losses: tensor(6.1018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1406 - Score: 0.0 Avg critic losses: tensor(6.4847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0001, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1407 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1408 - Score: 0.0 Avg critic losses: tensor(5.6320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1409 - Score: 0.0 Avg critic losses: tensor(6.0173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0025, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.1 -0.01] Episode 1410 - Score: 0.10000000149 Avg critic losses: tensor(8.5491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0031, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1411 - Score: 0.10000000149 Avg critic losses: tensor(6.6056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0014, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0027, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1412 - Score: 0.10000000149 Avg critic losses: tensor(8.5435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1413 - Score: 0.0 Avg critic losses: tensor(5.1864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0029, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1414 - Score: 0.10000000149 Avg critic losses: tensor(9.1666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1415 - Score: 0.0 Avg critic losses: tensor(6.2458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0024, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1416 - Score: 0.0 Avg critic losses: tensor(6.1098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1417 - Score: 0.10000000149 Avg critic losses: tensor(5.9803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1418 - Score: 0.0 Avg critic losses: tensor(5.1579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1419 - Score: 0.10000000149 Avg critic losses: tensor(6.5319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1420 - Score: 0.0 Episode 1420 - Mean score: 0.0327000005357 Avg critic losses: tensor(4.9930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1421 - Score: 0.0 Avg critic losses: tensor(5.5813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1422 - Score: 0.0 Avg critic losses: tensor(5.4012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1423 - Score: 0.10000000149 Avg critic losses: tensor(6.4801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1424 - Score: 0.0 Avg critic losses: tensor(7.9624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1425 - Score: 0.0 Avg critic losses: tensor(4.0475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1426 - Score: 0.0 Avg critic losses: tensor(5.9017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1427 - Score: 0.0 Avg critic losses: tensor(8.8182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1428 - Score: 0.0 Avg critic losses: tensor(6.2437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0036, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1429 - Score: 0.0 Avg critic losses: tensor(6.0342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) episode done in 12 time steps; scores: [-0.01 0. ] Episode 1430 - Score: 0.0 Avg critic losses: tensor(5.8017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0042, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1431 - Score: 0.0 Avg critic losses: tensor(6.6704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1432 - Score: 0.0 Avg critic losses: tensor(8.8975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0039, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1433 - Score: 0.0 Avg critic losses: tensor(7.7152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1434 - Score: 0.0 Avg critic losses: tensor(6.1311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1435 - Score: 0.10000000149 Avg critic losses: tensor(7.0119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1436 - Score: 0.0 Avg critic losses: tensor(6.3878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1437 - Score: 0.0 Avg critic losses: tensor(5.2150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1438 - Score: 0.0 Avg critic losses: tensor(6.2523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1439 - Score: 0.0 Avg critic losses: tensor(6.7487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1440 - Score: 0.0900000017136 Episode 1440 - Mean score: 0.0231000003777 Avg critic losses: tensor(6.8782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1441 - Score: 0.10000000149 Avg critic losses: tensor(6.1132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0044, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0046, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) episode done in 32 time steps; scores: [-0.01 0.1 ] Episode 1442 - Score: 0.10000000149 Avg critic losses: tensor(4.5124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1443 - Score: 0.0 Avg critic losses: tensor(7.3521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1444 - Score: 0.0 Avg critic losses: tensor(6.5431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1445 - Score: 0.0 Avg critic losses: tensor(4.9956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0021, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1446 - Score: 0.0 Avg critic losses: tensor(8.9565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0034, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0009, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0018, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1447 - Score: 0.10000000149 Avg critic losses: tensor(7.6613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0038, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1448 - Score: 0.0 Avg critic losses: tensor(7.3434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1449 - Score: 0.10000000149 Avg critic losses: tensor(5.2474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0032, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1450 - Score: 0.0 Avg critic losses: tensor(6.4573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1451 - Score: 0.10000000149 Avg critic losses: tensor(7.2004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1452 - Score: 0.10000000149 Avg critic losses: tensor(8.2774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0049, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1453 - Score: 0.10000000149 Avg critic losses: tensor(5.8645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1454 - Score: 0.0 Avg critic losses: tensor(7.9529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1455 - Score: 0.0 Avg critic losses: tensor(6.7277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.7451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1456 - Score: 0.0 Avg critic losses: tensor(5.4329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1457 - Score: 0.10000000149 Avg critic losses: tensor(8.8046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0040, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1458 - Score: 0.10000000149 Avg critic losses: tensor(8.4492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0037, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) episode done in 12 time steps; scores: [ 0. -0.01] Episode 1459 - Score: 0.0 Avg critic losses: tensor(5.4131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1460 - Score: 0.0 Episode 1460 - Mean score: 0.0246000003815 Avg critic losses: tensor(5.2301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1461 - Score: 0.0 Avg critic losses: tensor(9.7468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1462 - Score: 0.0 Avg critic losses: tensor(6.6310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0030, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0.1 -0.01] Episode 1463 - Score: 0.10000000149 Avg critic losses: tensor(7.5462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0. 0.09] Episode 1464 - Score: 0.0900000017136 Avg critic losses: tensor(6.3679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1465 - Score: 0.0 Avg critic losses: tensor(4.7996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1466 - Score: 0.0 Avg critic losses: tensor(6.2694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1467 - Score: 0.0 Avg critic losses: tensor(5.2447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0.1 -0.01] Episode 1468 - Score: 0.10000000149 Avg critic losses: tensor(9.8324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0045, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0043, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1469 - Score: 0.0 Avg critic losses: tensor(7.3061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1470 - Score: 0.0 Avg critic losses: tensor(6.2738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0053, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1471 - Score: 0.0 Avg critic losses: tensor(5.1393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1472 - Score: 0.0 Avg critic losses: tensor(5.4580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1473 - Score: 0.0 Avg critic losses: tensor(9.6391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) episode done in 47 time steps; scores: [ 0.1 -0.01] Episode 1474 - Score: 0.10000000149 Avg critic losses: tensor(6.6065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0051, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0052, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) episode done in 56 time steps; scores: [ 0.1 0.09] Episode 1475 - Score: 0.10000000149 Avg critic losses: tensor(6.5977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) episode done in 17 time steps; scores: [-0.01 0. ] Episode 1476 - Score: 0.0 Avg critic losses: tensor(6.9792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1477 - Score: 0.0 Avg critic losses: tensor(4.5119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1478 - Score: 0.0 Avg critic losses: tensor(6.2426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1479 - Score: 0.0 Avg critic losses: tensor(5.1802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [ 0.1 -0.01] Episode 1480 - Score: 0.10000000149 Episode 1480 - Mean score: 0.0276000004262 Avg critic losses: tensor(5.2812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.1747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1481 - Score: 0.0900000017136 Avg critic losses: tensor(7.1726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) episode done in 12 time steps; scores: [-0.01 0. ] Episode 1482 - Score: 0.0 Avg critic losses: tensor(5.4899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1483 - Score: 0.0 Avg critic losses: tensor(6.0856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0056, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1484 - Score: 0.10000000149 Avg critic losses: tensor(5.8365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) episode done in 12 time steps; scores: [-0.01 0. ] Episode 1485 - Score: 0.0 Avg critic losses: tensor(5.0092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1486 - Score: 0.10000000149 Avg critic losses: tensor(3.9972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0047, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0035, grad_fn=<MeanBackward0>) episode done in 47 time steps; scores: [-0.01 0.1 ] Episode 1487 - Score: 0.10000000149 Avg critic losses: tensor(7.1533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1488 - Score: 0.10000000149 Avg critic losses: tensor(7.2026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1489 - Score: 0.0 Avg critic losses: tensor(9.8989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1490 - Score: 0.10000000149 Avg critic losses: tensor(6.6446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1491 - Score: 0.0 Avg critic losses: tensor(6.3768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0054, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1492 - Score: 0.0 Avg critic losses: tensor(6.3971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1493 - Score: 0.10000000149 Avg critic losses: tensor(5.8158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1494 - Score: 0.0900000017136 Avg critic losses: tensor(5.4906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.7558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [ 0.1 -0.01] Episode 1495 - Score: 0.10000000149 Avg critic losses: tensor(6.1171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1496 - Score: 0.0 Avg critic losses: tensor(4.8804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0067, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) episode done in 48 time steps; scores: [-0.01 0.1 ] Episode 1497 - Score: 0.10000000149 Avg critic losses: tensor(8.0363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1498 - Score: 0.0900000017136 Avg critic losses: tensor(4.7701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) episode done in 34 time steps; scores: [-0.01 0.1 ] Episode 1499 - Score: 0.10000000149 Avg critic losses: tensor(6.5155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0059, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1500 - Score: 0.0900000017136 Episode 1500 - Mean score: 0.0373000005819 Avg critic losses: tensor(6.5092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1501 - Score: 0.10000000149 Avg critic losses: tensor(7.4984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1502 - Score: 0.0900000017136 Avg critic losses: tensor(4.7707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0070, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1503 - Score: 0.0900000017136 Avg critic losses: tensor(6.1663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0073, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [-0.01 0.1 ] Episode 1504 - Score: 0.10000000149 Avg critic losses: tensor(5.7496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0060, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1505 - Score: 0.10000000149 Avg critic losses: tensor(7.5871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 1506 - Score: 0.20000000298 Avg critic losses: tensor(6.4441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0057, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0061, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0041, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0064, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1507 - Score: 0.10000000149 Avg critic losses: tensor(7.5143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0050, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0058, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1508 - Score: 0.0900000017136 Avg critic losses: tensor(6.1976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0085, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) episode done in 59 time steps; scores: [ 0.2 -0.01] Episode 1509 - Score: 0.20000000298 Avg critic losses: tensor(4.1184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1510 - Score: 0.10000000149 Avg critic losses: tensor(4.6765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1511 - Score: 0.10000000149 Avg critic losses: tensor(5.3469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) episode done in 43 time steps; scores: [-0.01 0.1 ] Episode 1512 - Score: 0.10000000149 Avg critic losses: tensor(4.7768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1513 - Score: 0.10000000149 Avg critic losses: tensor(5.6797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1514 - Score: 0.0 Avg critic losses: tensor(5.8278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1515 - Score: 0.0900000017136 Avg critic losses: tensor(3.9792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0048, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0081, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1516 - Score: 0.10000000149 Avg critic losses: tensor(6.5329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0086, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.7387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1517 - Score: 0.10000000149 Avg critic losses: tensor(6.2612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0069, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0072, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1518 - Score: 0.0900000017136 Avg critic losses: tensor(7.4528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1519 - Score: 0.0900000017136 Avg critic losses: tensor(6.0777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.6540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0075, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1520 - Score: 0.10000000149 Episode 1520 - Mean score: 0.0508000008017 Avg critic losses: tensor(5.1798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1521 - Score: 0.0900000017136 Avg critic losses: tensor(5.2888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.5784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0066, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0080, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1522 - Score: 0.0900000017136 Avg critic losses: tensor(7.2069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) episode done in 32 time steps; scores: [ 0.1 -0.01] Episode 1523 - Score: 0.10000000149 Avg critic losses: tensor(6.5911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0079, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0068, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0101, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 1524 - Score: 0.10000000149 Avg critic losses: tensor(7.0387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0076, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1525 - Score: 0.0 Avg critic losses: tensor(5.7414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0078, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0087, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0071, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0082, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0055, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1526 - Score: 0.0900000017136 Avg critic losses: tensor(8.4296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0065, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0098, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1527 - Score: 0.0900000017136 Avg critic losses: tensor(6.2248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0062, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0063, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1528 - Score: 0.10000000149 Avg critic losses: tensor(5.2624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1529 - Score: 0.0 Avg critic losses: tensor(6.5680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0074, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0084, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1530 - Score: 0.0 Avg critic losses: tensor(7.8981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.6499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.6482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0090, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0096, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) episode done in 179 time steps; scores: [ 0.39000001 0.40000001] Episode 1531 - Score: 0.40000000596 Avg critic losses: tensor(6.8297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1532 - Score: 0.10000000149 Avg critic losses: tensor(7.1192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.7684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.3638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1533 - Score: 0.0900000017136 Avg critic losses: tensor(4.8198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0097, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1534 - Score: 0.10000000149 Avg critic losses: tensor(5.8036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0083, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1535 - Score: 0.10000000149 Avg critic losses: tensor(5.0653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0089, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0091, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1536 - Score: 0.10000000149 Avg critic losses: tensor(4.4660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1537 - Score: 0.0 Avg critic losses: tensor(5.3506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1538 - Score: 0.0900000017136 Avg critic losses: tensor(5.8468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) episode done in 105 time steps; scores: [ 0.19 0.2 ] Episode 1539 - Score: 0.20000000298 Avg critic losses: tensor(7.3243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1540 - Score: 0.10000000149 Episode 1540 - Mean score: 0.0673000010662 Avg critic losses: tensor(5.7990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0102, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0104, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.3928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1541 - Score: 0.10000000149 Avg critic losses: tensor(5.3285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1542 - Score: 0.0 Avg critic losses: tensor(4.5625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0095, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1543 - Score: 0.10000000149 Avg critic losses: tensor(6.7142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1544 - Score: 0.10000000149 Avg critic losses: tensor(5.2047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1545 - Score: 0.10000000149 Avg critic losses: tensor(6.7161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0103, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) episode done in 32 time steps; scores: [-0.01 0.1 ] Episode 1546 - Score: 0.10000000149 Avg critic losses: tensor(7.6567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 1547 - Score: 0.190000003204 Avg critic losses: tensor(7.5657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0092, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) episode done in 47 time steps; scores: [-0.01 0.1 ] Episode 1548 - Score: 0.10000000149 Avg critic losses: tensor(5.2161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1549 - Score: 0.10000000149 Avg critic losses: tensor(7.5059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) episode done in 47 time steps; scores: [-0.01 0.1 ] Episode 1550 - Score: 0.10000000149 Avg critic losses: tensor(7.7656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1551 - Score: 0.10000000149 Avg critic losses: tensor(5.8319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0116, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1552 - Score: 0.10000000149 Avg critic losses: tensor(8.4649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1553 - Score: 0.0900000017136 Avg critic losses: tensor(6.4631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0099, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1554 - Score: 0.10000000149 Avg critic losses: tensor(6.0913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1555 - Score: 0.10000000149 Avg critic losses: tensor(6.0634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0126, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0100, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0115, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0077, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1556 - Score: 0.10000000149 Avg critic losses: tensor(7.4543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1557 - Score: 0.10000000149 Avg critic losses: tensor(4.7634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0106, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) episode done in 47 time steps; scores: [ 0.1 -0.01] Episode 1558 - Score: 0.10000000149 Avg critic losses: tensor(6.4490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0121, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0105, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0113, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0094, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1559 - Score: 0.10000000149 Avg critic losses: tensor(5.9226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0112, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1560 - Score: 0.10000000149 Episode 1560 - Mean score: 0.0781000012346 Avg critic losses: tensor(5.0060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1561 - Score: 0.10000000149 Avg critic losses: tensor(6.8613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.7780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1562 - Score: 0.0900000017136 Avg critic losses: tensor(7.5199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1563 - Score: 0.10000000149 Avg critic losses: tensor(5.7225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) episode done in 47 time steps; scores: [ 0.1 -0.01] Episode 1564 - Score: 0.10000000149 Avg critic losses: tensor(5.4361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0129, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 1565 - Score: 0.190000003204 Avg critic losses: tensor(5.6758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1566 - Score: 0.0 Avg critic losses: tensor(5.5748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0120, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1567 - Score: 0.10000000149 Avg critic losses: tensor(5.6470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 1568 - Score: 0.10000000149 Avg critic losses: tensor(6.3023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1569 - Score: 0.10000000149 Avg critic losses: tensor(7.9385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1570 - Score: 0.10000000149 Avg critic losses: tensor(8.8970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) episode done in 64 time steps; scores: [ 0.1 0.19] Episode 1571 - Score: 0.190000003204 Avg critic losses: tensor(6.7026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0130, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1572 - Score: 0.10000000149 Avg critic losses: tensor(6.3634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0118, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) episode done in 39 time steps; scores: [-0.01 0.1 ] Episode 1573 - Score: 0.10000000149 Avg critic losses: tensor(6.7904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [ 0.1 -0.01] Episode 1574 - Score: 0.10000000149 Avg critic losses: tensor(6.7788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1575 - Score: 0.10000000149 Avg critic losses: tensor(8.2556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0109, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1576 - Score: 0.10000000149 Avg critic losses: tensor(5.0601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0093, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.7529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1577 - Score: 0.10000000149 Avg critic losses: tensor(7.5681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1578 - Score: 0.0900000017136 Avg critic losses: tensor(6.3214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0128, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1579 - Score: 0.0900000017136 Avg critic losses: tensor(7.1558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1580 - Score: 0.0900000017136 Episode 1580 - Mean score: 0.0926000014693 Avg critic losses: tensor(8.3304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1581 - Score: 0.10000000149 Avg critic losses: tensor(7.4506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1582 - Score: 0.0900000017136 Avg critic losses: tensor(6.5866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0114, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0107, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) episode done in 48 time steps; scores: [ 0.1 -0.01] Episode 1583 - Score: 0.10000000149 Avg critic losses: tensor(7.0698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0133, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1584 - Score: 0.0900000017136 Avg critic losses: tensor(6.1201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0110, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0111, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0139, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0137, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1585 - Score: 0.0900000017136 Avg critic losses: tensor(6.5677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1586 - Score: 0.0 Avg critic losses: tensor(7.0459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.6109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1587 - Score: 0.0900000017136 Avg critic losses: tensor(6.1938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1588 - Score: 0.10000000149 Avg critic losses: tensor(6.5645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0117, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0125, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1589 - Score: 0.10000000149 Avg critic losses: tensor(5.0989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0132, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.4189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) episode done in 65 time steps; scores: [ 0.2 0.09] Episode 1590 - Score: 0.20000000298 Avg critic losses: tensor(3.9381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1591 - Score: 0.10000000149 Avg critic losses: tensor(4.9516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1592 - Score: 0.0900000017136 Avg critic losses: tensor(9.6994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0134, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1593 - Score: 0.10000000149 Avg critic losses: tensor(6.5920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0123, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1594 - Score: 0.10000000149 Avg critic losses: tensor(5.7810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0152, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1595 - Score: 0.0 Avg critic losses: tensor(4.8688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) episode done in 47 time steps; scores: [-0.01 0.1 ] Episode 1596 - Score: 0.10000000149 Avg critic losses: tensor(6.2527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0124, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1597 - Score: 0.10000000149 Avg critic losses: tensor(5.5397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0141, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 0.09] Episode 1598 - Score: 0.10000000149 Avg critic losses: tensor(8.4208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0108, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1599 - Score: 0.0 Avg critic losses: tensor(9.3549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1600 - Score: 0.0900000017136 Episode 1600 - Mean score: 0.0974000015482 Avg critic losses: tensor(5.5472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0145, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0136, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0122, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0119, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0151, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0131, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [-0.01 0.1 ] Episode 1601 - Score: 0.10000000149 Avg critic losses: tensor(6.8240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0127, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0088, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0135, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1602 - Score: 0.10000000149 Avg critic losses: tensor(5.7765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.6335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1603 - Score: 0.10000000149 Avg critic losses: tensor(7.6343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0144, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1604 - Score: 0.10000000149 Avg critic losses: tensor(5.6323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1605 - Score: 0.0 Avg critic losses: tensor(6.6868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1606 - Score: 0.0900000017136 Avg critic losses: tensor(7.0184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1607 - Score: 0.0900000017136 Avg critic losses: tensor(5.4107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0143, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1608 - Score: 0.10000000149 Avg critic losses: tensor(5.2399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0138, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1609 - Score: 0.0900000017136 Avg critic losses: tensor(8.1673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1610 - Score: 0.10000000149 Avg critic losses: tensor(6.6453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0148, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [-0.01 0.1 ] Episode 1611 - Score: 0.10000000149 Avg critic losses: tensor(5.6077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0150, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) episode done in 45 time steps; scores: [-0.01 0.1 ] Episode 1612 - Score: 0.10000000149 Avg critic losses: tensor(5.8578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0147, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1613 - Score: 0.10000000149 Avg critic losses: tensor(7.8405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0140, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.4575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0168, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(2.9473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) episode done in 47 time steps; scores: [-0.01 0.1 ] Episode 1614 - Score: 0.10000000149 Avg critic losses: tensor(8.0568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1615 - Score: 0.10000000149 Avg critic losses: tensor(6.4670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1616 - Score: 0.0900000017136 Avg critic losses: tensor(6.1572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0149, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.7939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.5703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1617 - Score: 0.0900000017136 Avg critic losses: tensor(4.7987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0161, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1618 - Score: 0.10000000149 Avg critic losses: tensor(6.3728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1619 - Score: 0.10000000149 Avg critic losses: tensor(6.4633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1620 - Score: 0.0900000017136 Episode 1620 - Mean score: 0.0954000015184 Avg critic losses: tensor(4.5877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.5898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0154, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0183, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.6725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 1621 - Score: 0.20000000298 Avg critic losses: tensor(6.3413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0146, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0164, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1622 - Score: 0.0900000017136 Avg critic losses: tensor(6.3108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0160, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1623 - Score: 0.10000000149 Avg critic losses: tensor(5.5918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0167, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [-0.01 0.1 ] Episode 1624 - Score: 0.10000000149 Avg critic losses: tensor(9.4767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0163, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0165, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 1625 - Score: 0.10000000149 Avg critic losses: tensor(4.5124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.6640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0166, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.6075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) episode done in 68 time steps; scores: [ 0.2 0.09] Episode 1626 - Score: 0.20000000298 Avg critic losses: tensor(7.1810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0159, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0155, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0153, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) episode done in 57 time steps; scores: [ 0.1 0.09] Episode 1627 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0176, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1628 - Score: 0.10000000149 Avg critic losses: tensor(6.0404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0177, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0157, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 1629 - Score: 0.10000000149 Avg critic losses: tensor(6.3465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1630 - Score: 0.10000000149 Avg critic losses: tensor(6.2242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0170, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.3345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0156, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0162, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1631 - Score: 0.10000000149 Avg critic losses: tensor(7.4071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0142, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1632 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0171, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0181, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1633 - Score: 0.10000000149 Avg critic losses: tensor(6.7669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) episode done in 42 time steps; scores: [ 0.1 -0.01] Episode 1634 - Score: 0.10000000149 Avg critic losses: tensor(5.9807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1635 - Score: 0.10000000149 Avg critic losses: tensor(5.7021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1636 - Score: 0.10000000149 Avg critic losses: tensor(6.0798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1637 - Score: 0.10000000149 Avg critic losses: tensor(6.0213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0184, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1638 - Score: 0.0900000017136 Avg critic losses: tensor(7.1868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0190, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.09 0.1 ] Episode 1639 - Score: 0.10000000149 Avg critic losses: tensor(7.4435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [-0.01 0.1 ] Episode 1640 - Score: 0.10000000149 Episode 1640 - Mean score: 0.0978000015393 Avg critic losses: tensor(8.1939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0158, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1641 - Score: 0.10000000149 Avg critic losses: tensor(6.3340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0210, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0182, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 0.09] Episode 1642 - Score: 0.10000000149 Avg critic losses: tensor(8.4732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0175, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1643 - Score: 0.10000000149 Avg critic losses: tensor(5.9452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0208, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 1644 - Score: 0.10000000149 Avg critic losses: tensor(5.7726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [-0.01 0.1 ] Episode 1645 - Score: 0.10000000149 Avg critic losses: tensor(5.2332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1646 - Score: 0.0 Avg critic losses: tensor(8.3337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [-0.01 0. ] Episode 1647 - Score: 0.0 Avg critic losses: tensor(7.8196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0174, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0191, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) episode done in 33 time steps; scores: [ 0.1 -0.01] Episode 1648 - Score: 0.10000000149 Avg critic losses: tensor(9.6007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0178, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0192, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1649 - Score: 0.10000000149 Avg critic losses: tensor(4.9696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) episode done in 32 time steps; scores: [ 0.1 -0.01] Episode 1650 - Score: 0.10000000149 Avg critic losses: tensor(6.8348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1651 - Score: 0.10000000149 Avg critic losses: tensor(8.7318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0195, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [-0.01 0.1 ] Episode 1652 - Score: 0.10000000149 Avg critic losses: tensor(6.8607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0.1 -0.01] Episode 1653 - Score: 0.10000000149 Avg critic losses: tensor(9.2276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0189, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1654 - Score: 0.10000000149 Avg critic losses: tensor(5.5718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1655 - Score: 0.10000000149 Avg critic losses: tensor(6.3437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) episode done in 47 time steps; scores: [-0.01 0.1 ] Episode 1656 - Score: 0.10000000149 Avg critic losses: tensor(5.7374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0203, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) episode done in 48 time steps; scores: [ 0.1 -0.01] Episode 1657 - Score: 0.10000000149 Avg critic losses: tensor(9.5967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0188, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0212, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0196, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0173, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) episode done in 65 time steps; scores: [ 0.2 0.09] Episode 1658 - Score: 0.20000000298 Avg critic losses: tensor(8.0666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1659 - Score: 0.10000000149 Avg critic losses: tensor(5.8852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0204, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0186, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0187, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0179, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) episode done in 61 time steps; scores: [ 0.09 0.1 ] Episode 1660 - Score: 0.10000000149 Episode 1660 - Mean score: 0.0970000015199 Avg critic losses: tensor(7.2233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0169, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0193, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0200, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0206, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) episode done in 44 time steps; scores: [-0.01 0.1 ] Episode 1661 - Score: 0.10000000149 Avg critic losses: tensor(4.2026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1662 - Score: 0.10000000149 Avg critic losses: tensor(5.7104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1663 - Score: 0.10000000149 Avg critic losses: tensor(6.5488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0194, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0172, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0209, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) episode done in 60 time steps; scores: [ 0.09 0.1 ] Episode 1664 - Score: 0.10000000149 Avg critic losses: tensor(7.0701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0197, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0180, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1665 - Score: 0.10000000149 Avg critic losses: tensor(6.7500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1666 - Score: 0.0 Avg critic losses: tensor(7.5416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1667 - Score: 0.0900000017136 Avg critic losses: tensor(6.9706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1668 - Score: 0.10000000149 Avg critic losses: tensor(5.4758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0201, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1669 - Score: 0.10000000149 Avg critic losses: tensor(9.8150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1670 - Score: 0.10000000149 Avg critic losses: tensor(8.1575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0202, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) episode done in 59 time steps; scores: [ 0.09 0.1 ] Episode 1671 - Score: 0.10000000149 Avg critic losses: tensor(5.2141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1672 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0198, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) episode done in 53 time steps; scores: [ 0.1 -0.01] Episode 1673 - Score: 0.10000000149 Avg critic losses: tensor(6.4272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1674 - Score: 0.10000000149 Avg critic losses: tensor(6.7059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0220, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) episode done in 56 time steps; scores: [ 0.1 0.09] Episode 1675 - Score: 0.10000000149 Avg critic losses: tensor(7.1324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1676 - Score: 0.0900000017136 Avg critic losses: tensor(6.7365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0185, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) episode done in 89 time steps; scores: [ 0.2 0.19] Episode 1677 - Score: 0.20000000298 Avg critic losses: tensor(6.4352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) episode done in 61 time steps; scores: [ 0.1 0.09] Episode 1678 - Score: 0.10000000149 Avg critic losses: tensor(4.8882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) episode done in 61 time steps; scores: [ 0.1 0.09] Episode 1679 - Score: 0.10000000149 Avg critic losses: tensor(9.1112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0216, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) episode done in 61 time steps; scores: [ 0.1 0.09] Episode 1680 - Score: 0.10000000149 Episode 1680 - Mean score: 0.0964000014961 Avg critic losses: tensor(8.7678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0. ] Episode 1681 - Score: 0.0 Avg critic losses: tensor(7.3508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1682 - Score: 0.10000000149 Avg critic losses: tensor(7.8730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1683 - Score: 0.0900000017136 Avg critic losses: tensor(7.0321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1684 - Score: 0.10000000149 Avg critic losses: tensor(8.1556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1685 - Score: 0.10000000149 Avg critic losses: tensor(7.8964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0225, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1686 - Score: 0.10000000149 Avg critic losses: tensor(9.8115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1687 - Score: 0.10000000149 Avg critic losses: tensor(7.0632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0223, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1688 - Score: 0.10000000149 Avg critic losses: tensor(9.1674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1689 - Score: 0.10000000149 Avg critic losses: tensor(6.1839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [-0.01 0.1 ] Episode 1690 - Score: 0.10000000149 Avg critic losses: tensor(6.6994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1691 - Score: 0.10000000149 Avg critic losses: tensor(6.7427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1692 - Score: 0.10000000149 Avg critic losses: tensor(6.4016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.5647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [ 0. -0.01] Episode 1693 - Score: 0.0 Avg critic losses: tensor(5.1567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1694 - Score: 0.10000000149 Avg critic losses: tensor(5.5716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0215, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1695 - Score: 0.10000000149 Avg critic losses: tensor(6.8958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1696 - Score: 0.10000000149 Avg critic losses: tensor(9.2531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0199, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1697 - Score: 0.10000000149 Avg critic losses: tensor(7.9773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1698 - Score: 0.10000000149 Avg critic losses: tensor(5.3255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0226, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1699 - Score: 0.10000000149 Avg critic losses: tensor(5.2046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 0.09] Episode 1700 - Score: 0.10000000149 Episode 1700 - Mean score: 0.0969000014849 Avg critic losses: tensor(6.1499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1701 - Score: 0.0 Avg critic losses: tensor(8.3969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0218, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1702 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [ 0. 0.09] Episode 1703 - Score: 0.0900000017136 Avg critic losses: tensor(9.1548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1704 - Score: 0.10000000149 Avg critic losses: tensor(6.3371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1705 - Score: 0.0900000017136 Avg critic losses: tensor(8.9963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1706 - Score: 0.10000000149 Avg critic losses: tensor(7.2920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1707 - Score: 0.10000000149 Avg critic losses: tensor(7.7678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1708 - Score: 0.10000000149 Avg critic losses: tensor(5.9077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1709 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0219, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1710 - Score: 0.10000000149 Avg critic losses: tensor(5.5059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0213, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1711 - Score: 0.10000000149 Avg critic losses: tensor(7.1481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1712 - Score: 0.10000000149 Avg critic losses: tensor(6.4560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0233, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1713 - Score: 0.10000000149 Avg critic losses: tensor(5.6839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1714 - Score: 0.10000000149 Avg critic losses: tensor(6.2524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1715 - Score: 0.10000000149 Avg critic losses: tensor(6.4223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1716 - Score: 0.10000000149 Avg critic losses: tensor(7.4009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1717 - Score: 0.10000000149 Avg critic losses: tensor(6.3279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0214, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0211, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1718 - Score: 0.10000000149 Avg critic losses: tensor(6.3688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1719 - Score: 0.0 Avg critic losses: tensor(7.9701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1720 - Score: 0.10000000149 Episode 1720 - Mean score: 0.0963000014611 Avg critic losses: tensor(6.9700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1721 - Score: 0.0 Avg critic losses: tensor(5.4939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1722 - Score: 0.10000000149 Avg critic losses: tensor(6.2737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1723 - Score: 0.10000000149 Avg critic losses: tensor(7.8893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0217, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0207, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1724 - Score: 0.10000000149 Avg critic losses: tensor(8.5328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0230, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) episode done in 90 time steps; scores: [ 0.19 0.2 ] Episode 1725 - Score: 0.20000000298 Avg critic losses: tensor(6.9784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) episode done in 62 time steps; scores: [ 0.1 0.09] Episode 1726 - Score: 0.10000000149 Avg critic losses: tensor(9.2948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0224, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) episode done in 32 time steps; scores: [-0.01 0.1 ] Episode 1727 - Score: 0.10000000149 Avg critic losses: tensor(7.8133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) episode done in 53 time steps; scores: [ 0.09 0.1 ] Episode 1728 - Score: 0.10000000149 Avg critic losses: tensor(5.0143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) episode done in 41 time steps; scores: [ 0.1 -0.01] Episode 1729 - Score: 0.10000000149 Avg critic losses: tensor(7.0869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0241, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1730 - Score: 0.10000000149 Avg critic losses: tensor(8.0088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0237, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) episode done in 60 time steps; scores: [ 0.1 0.09] Episode 1731 - Score: 0.10000000149 Avg critic losses: tensor(7.1519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0227, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0235, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) episode done in 89 time steps; scores: [ 0.09 0.2 ] Episode 1732 - Score: 0.20000000298 Avg critic losses: tensor(8.7327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0228, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0232, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 1733 - Score: 0.10000000149 Avg critic losses: tensor(8.0913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0242, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0205, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1734 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1735 - Score: 0.10000000149 Avg critic losses: tensor(7.5426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0231, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 1736 - Score: 0.190000003204 Avg critic losses: tensor(5.4936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 1737 - Score: 0.190000003204 Avg critic losses: tensor(8.3829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1738 - Score: 0.0900000017136 Avg critic losses: tensor(6.4433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1739 - Score: 0.10000000149 Avg critic losses: tensor(6.1644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0222, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0.1 -0.01] Episode 1740 - Score: 0.10000000149 Episode 1740 - Mean score: 0.0962000014633 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 1741 - Score: 0.20000000298 Avg critic losses: tensor(6.6439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.1 0.19] Episode 1742 - Score: 0.190000003204 Avg critic losses: tensor(7.5767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0229, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 1743 - Score: 0.10000000149 Avg critic losses: tensor(5.6336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0240, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1744 - Score: 0.10000000149 Avg critic losses: tensor(7.9274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.09 0.2 ] Episode 1745 - Score: 0.20000000298 Avg critic losses: tensor(9.9984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1746 - Score: 0.10000000149 Avg critic losses: tensor(6.5966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0239, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1747 - Score: 0.10000000149 Avg critic losses: tensor(7.4727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1748 - Score: 0.0900000017136 Avg critic losses: tensor(7.8258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1749 - Score: 0.10000000149 Avg critic losses: tensor(7.6445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0236, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1750 - Score: 0.10000000149 Avg critic losses: tensor(7.9198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0252, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1751 - Score: 0.10000000149 Avg critic losses: tensor(7.5783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1752 - Score: 0.10000000149 Avg critic losses: tensor(7.6312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1753 - Score: 0.10000000149 Avg critic losses: tensor(6.1756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1754 - Score: 0.10000000149 Avg critic losses: tensor(8.2840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0238, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 1755 - Score: 0.190000003204 Avg critic losses: tensor(6.6593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1756 - Score: 0.0900000017136 Avg critic losses: tensor(7.2835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0244, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.1 0.09] Episode 1757 - Score: 0.10000000149 Avg critic losses: tensor(5.6096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1758 - Score: 0.10000000149 Avg critic losses: tensor(9.9148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0253, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1759 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0221, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0234, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0243, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 -0.01] Episode 1760 - Score: 0.10000000149 Episode 1760 - Mean score: 0.100800001547 Avg critic losses: tensor(6.7413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) episode done in 47 time steps; scores: [-0.01 0.1 ] Episode 1761 - Score: 0.10000000149 Avg critic losses: tensor(7.5535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1762 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0245, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0247, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 1763 - Score: 0.20000000298 Avg critic losses: tensor(7.3061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0251, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1764 - Score: 0.10000000149 Avg critic losses: tensor(5.4257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0255, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 1765 - Score: 0.20000000298 Avg critic losses: tensor(6.6395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1766 - Score: 0.10000000149 Avg critic losses: tensor(9.3573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1767 - Score: 0.0900000017136 Avg critic losses: tensor(8.7129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1768 - Score: 0.0900000017136 Avg critic losses: tensor(8.7434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) episode done in 49 time steps; scores: [ 0.1 -0.01] Episode 1769 - Score: 0.10000000149 Avg critic losses: tensor(5.6648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.7768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1770 - Score: 0.10000000149 Avg critic losses: tensor(5.3716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) episode done in 86 time steps; scores: [ 0.09 0.2 ] Episode 1771 - Score: 0.20000000298 Avg critic losses: tensor(9.0178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.1 0.09] Episode 1772 - Score: 0.10000000149 Avg critic losses: tensor(6.8809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 1773 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0249, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0259, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 1774 - Score: 0.20000000298 Avg critic losses: tensor(6.9072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1775 - Score: 0.10000000149 Avg critic losses: tensor(9.1273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0246, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) episode done in 70 time steps; scores: [ 0.1 0.19] Episode 1776 - Score: 0.190000003204 Avg critic losses: tensor(9.6042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.09 0.1 ] Episode 1777 - Score: 0.10000000149 Avg critic losses: tensor(9.1316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) episode done in 71 time steps; scores: [ 0.2 0.09] Episode 1778 - Score: 0.20000000298 Avg critic losses: tensor(7.3512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0248, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) episode done in 64 time steps; scores: [ 0.1 0.09] Episode 1779 - Score: 0.10000000149 Avg critic losses: tensor(8.0032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 1780 - Score: 0.10000000149 Episode 1780 - Mean score: 0.107700001653 Avg critic losses: tensor(8.0531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) episode done in 57 time steps; scores: [ 0.09 0.1 ] Episode 1781 - Score: 0.10000000149 Avg critic losses: tensor(9.9076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1782 - Score: 0.0900000017136 Avg critic losses: tensor(5.8464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) episode done in 71 time steps; scores: [ 0.2 0.09] Episode 1783 - Score: 0.20000000298 Avg critic losses: tensor(7.0218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 0.09] Episode 1784 - Score: 0.10000000149 Avg critic losses: tensor(9.0261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.09 0.1 ] Episode 1785 - Score: 0.10000000149 Avg critic losses: tensor(6.7607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) episode done in 32 time steps; scores: [-0.01 0.1 ] Episode 1786 - Score: 0.10000000149 Avg critic losses: tensor(7.2401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 1787 - Score: 0.20000000298 Avg critic losses: tensor(8.0742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1788 - Score: 0.10000000149 Avg critic losses: tensor(7.6862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0258, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) episode done in 53 time steps; scores: [ 0.1 0.09] Episode 1789 - Score: 0.10000000149 Avg critic losses: tensor(4.3201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1790 - Score: 0.10000000149 Avg critic losses: tensor(6.5653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) episode done in 32 time steps; scores: [-0.01 0.1 ] Episode 1791 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1792 - Score: 0.10000000149 Avg critic losses: tensor(5.6617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) episode done in 33 time steps; scores: [-0.01 0.1 ] Episode 1793 - Score: 0.10000000149 Avg critic losses: tensor(7.2781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1794 - Score: 0.10000000149 Avg critic losses: tensor(7.6250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0265, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1795 - Score: 0.0900000017136 Avg critic losses: tensor(7.4624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 1796 - Score: 0.0 Avg critic losses: tensor(8.7382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1797 - Score: 0.10000000149 Avg critic losses: tensor(7.1330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1798 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0279, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 1799 - Score: 0.20000000298 Avg critic losses: tensor(8.0507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1800 - Score: 0.10000000149 Episode 1800 - Mean score: 0.111600001715 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) episode done in 71 time steps; scores: [ 0.2 0.09] Episode 1801 - Score: 0.20000000298 Avg critic losses: tensor(8.3183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1802 - Score: 0.10000000149 Avg critic losses: tensor(9.7406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1803 - Score: 0.10000000149 Avg critic losses: tensor(8.2082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1804 - Score: 0.0900000017136 Avg critic losses: tensor(8.1732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) episode done in 69 time steps; scores: [ 0.1 0.19] Episode 1805 - Score: 0.190000003204 Avg critic losses: tensor(6.8111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0268, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0256, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1806 - Score: 0.10000000149 Avg critic losses: tensor(6.9165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1807 - Score: 0.10000000149 Avg critic losses: tensor(7.5072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 1808 - Score: 0.20000000298 Avg critic losses: tensor(8.6607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0250, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0264, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. -0.01] Episode 1809 - Score: 0.0 Avg critic losses: tensor(6.0125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 1810 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1811 - Score: 0.10000000149 Avg critic losses: tensor(9.6864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0271, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1812 - Score: 0.10000000149 Avg critic losses: tensor(7.1009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1813 - Score: 0.10000000149 Avg critic losses: tensor(5.8773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0277, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0267, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1814 - Score: 0.10000000149 Avg critic losses: tensor(6.6646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1815 - Score: 0.10000000149 Avg critic losses: tensor(6.9596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 1816 - Score: 0.20000000298 Avg critic losses: tensor(6.3869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1817 - Score: 0.10000000149 Avg critic losses: tensor(6.8793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0260, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1818 - Score: 0.10000000149 Avg critic losses: tensor(8.1163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0272, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1819 - Score: 0.10000000149 Avg critic losses: tensor(8.8645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1820 - Score: 0.10000000149 Episode 1820 - Mean score: 0.117600001805 Avg critic losses: tensor(8.3563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0281, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1821 - Score: 0.10000000149 Avg critic losses: tensor(5.6783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0274, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0262, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0273, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0257, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1822 - Score: 0.10000000149 Avg critic losses: tensor(7.5508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0269, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1823 - Score: 0.10000000149 Avg critic losses: tensor(9.6402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0261, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0280, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0266, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0254, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1824 - Score: 0.10000000149 Avg critic losses: tensor(7.4079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1825 - Score: 0.0900000017136 Avg critic losses: tensor(8.2799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1826 - Score: 0.10000000149 Avg critic losses: tensor(7.2114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0263, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) episode done in 53 time steps; scores: [ 0.09 0.1 ] Episode 1827 - Score: 0.10000000149 Avg critic losses: tensor(5.2200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1828 - Score: 0.10000000149 Avg critic losses: tensor(9.9141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) episode done in 57 time steps; scores: [ 0.1 0.09] Episode 1829 - Score: 0.10000000149 Avg critic losses: tensor(8.1434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0270, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.09 0.1 ] Episode 1830 - Score: 0.10000000149 Avg critic losses: tensor(6.6790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1831 - Score: 0.10000000149 Avg critic losses: tensor(6.9559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1832 - Score: 0.10000000149 Avg critic losses: tensor(8.1257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1833 - Score: 0.10000000149 Avg critic losses: tensor(6.5980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1834 - Score: 0.10000000149 Avg critic losses: tensor(7.0398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 1835 - Score: 0.10000000149 Avg critic losses: tensor(7.1191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1836 - Score: 0.10000000149 Avg critic losses: tensor(6.9943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1837 - Score: 0.10000000149 Avg critic losses: tensor(7.4558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1838 - Score: 0.10000000149 Avg critic losses: tensor(7.4684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [-0.01 0.1 ] Episode 1839 - Score: 0.10000000149 Avg critic losses: tensor(6.6732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1840 - Score: 0.10000000149 Episode 1840 - Mean score: 0.11580000177 Avg critic losses: tensor(8.7281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1841 - Score: 0.10000000149 Avg critic losses: tensor(8.9510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 1842 - Score: 0.0 Avg critic losses: tensor(5.1703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) episode done in 69 time steps; scores: [ 0.2 0.09] Episode 1843 - Score: 0.20000000298 Avg critic losses: tensor(6.0405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1844 - Score: 0.10000000149 Avg critic losses: tensor(7.5028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1845 - Score: 0.10000000149 Avg critic losses: tensor(7.0533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1846 - Score: 0.10000000149 Avg critic losses: tensor(9.9803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0283, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1847 - Score: 0.10000000149 Avg critic losses: tensor(5.7972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1848 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1849 - Score: 0.0900000017136 Avg critic losses: tensor(8.8980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 -0.01] Episode 1850 - Score: 0.10000000149 Avg critic losses: tensor(6.6348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1851 - Score: 0.10000000149 Avg critic losses: tensor(6.2398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1852 - Score: 0.10000000149 Avg critic losses: tensor(7.5118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0296, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1853 - Score: 0.10000000149 Avg critic losses: tensor(8.9246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1854 - Score: 0.10000000149 Avg critic losses: tensor(4.6780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1855 - Score: 0.10000000149 Avg critic losses: tensor(8.1369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0276, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.1 0.09] Episode 1856 - Score: 0.10000000149 Avg critic losses: tensor(6.1103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1857 - Score: 0.10000000149 Avg critic losses: tensor(8.0571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1858 - Score: 0.10000000149 Avg critic losses: tensor(6.1792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1859 - Score: 0.10000000149 Avg critic losses: tensor(8.0848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1860 - Score: 0.10000000149 Episode 1860 - Mean score: 0.112100001704 Avg critic losses: tensor(6.8860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1861 - Score: 0.10000000149 Avg critic losses: tensor(9.7616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1862 - Score: 0.10000000149 Avg critic losses: tensor(6.2526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1863 - Score: 0.10000000149 Avg critic losses: tensor(4.3385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1864 - Score: 0.10000000149 Avg critic losses: tensor(6.6314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0298, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1865 - Score: 0.10000000149 Avg critic losses: tensor(8.6886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0290, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1866 - Score: 0.10000000149 Avg critic losses: tensor(5.3518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0305, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.1 0.09] Episode 1867 - Score: 0.10000000149 Avg critic losses: tensor(8.5616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) episode done in 53 time steps; scores: [ 0.1 0.09] Episode 1868 - Score: 0.10000000149 Avg critic losses: tensor(9.7282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1869 - Score: 0.10000000149 Avg critic losses: tensor(6.5779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.6053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) episode done in 69 time steps; scores: [ 0.2 0.09] Episode 1870 - Score: 0.20000000298 Avg critic losses: tensor(6.2385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.7573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0275, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) episode done in 129 time steps; scores: [ 0.29 0.3 ] Episode 1871 - Score: 0.30000000447 Avg critic losses: tensor(8.9299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [-0.01 0.1 ] Episode 1872 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1873 - Score: 0.10000000149 Avg critic losses: tensor(8.3933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1874 - Score: 0.10000000149 Avg critic losses: tensor(8.3019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1875 - Score: 0.10000000149 Avg critic losses: tensor(6.4412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0302, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1876 - Score: 0.10000000149 Avg critic losses: tensor(8.3052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0291, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1877 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1878 - Score: 0.10000000149 Avg critic losses: tensor(5.2100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0293, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) episode done in 70 time steps; scores: [ 0.2 0.09] Episode 1879 - Score: 0.20000000298 Avg critic losses: tensor(8.0528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1880 - Score: 0.0900000017136 Episode 1880 - Mean score: 0.109300001655 Avg critic losses: tensor(6.0101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1881 - Score: 0.10000000149 Avg critic losses: tensor(8.2460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0297, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 1882 - Score: 0.20000000298 Avg critic losses: tensor(7.6750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1883 - Score: 0.10000000149 Avg critic losses: tensor(7.8351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1884 - Score: 0.10000000149 Avg critic losses: tensor(7.6641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0284, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1885 - Score: 0.10000000149 Avg critic losses: tensor(8.2606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1886 - Score: 0.10000000149 Avg critic losses: tensor(7.8775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0294, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1887 - Score: 0.10000000149 Avg critic losses: tensor(7.6183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.5533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1888 - Score: 0.10000000149 Avg critic losses: tensor(7.7354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0282, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0295, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1889 - Score: 0.10000000149 Avg critic losses: tensor(4.9572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1890 - Score: 0.10000000149 Avg critic losses: tensor(7.5242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1891 - Score: 0.10000000149 Avg critic losses: tensor(7.1376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1892 - Score: 0.10000000149 Avg critic losses: tensor(8.6610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1893 - Score: 0.10000000149 Avg critic losses: tensor(6.5554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1894 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 1895 - Score: 0.20000000298 Avg critic losses: tensor(5.8468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.1 0.19] Episode 1896 - Score: 0.190000003204 Avg critic losses: tensor(8.6125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1897 - Score: 0.10000000149 Avg critic losses: tensor(6.8461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1898 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.1 0.19] Episode 1899 - Score: 0.190000003204 Avg critic losses: tensor(7.8200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1900 - Score: 0.10000000149 Episode 1900 - Mean score: 0.111300001685 Avg critic losses: tensor(8.2107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1901 - Score: 0.10000000149 Avg critic losses: tensor(5.9604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0306, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1902 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0309, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1903 - Score: 0.10000000149 Avg critic losses: tensor(9.0743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1904 - Score: 0.0900000017136 Avg critic losses: tensor(7.8722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1905 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1906 - Score: 0.10000000149 Avg critic losses: tensor(9.3662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1907 - Score: 0.10000000149 Avg critic losses: tensor(6.5306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0304, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0310, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1908 - Score: 0.10000000149 Avg critic losses: tensor(8.5392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1909 - Score: 0.10000000149 Avg critic losses: tensor(6.4862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1910 - Score: 0.10000000149 Avg critic losses: tensor(8.8356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) episode done in 88 time steps; scores: [ 0.2 0.19] Episode 1911 - Score: 0.20000000298 Avg critic losses: tensor(6.8060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0288, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0289, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) episode done in 71 time steps; scores: [ 0.09 0.2 ] Episode 1912 - Score: 0.20000000298 Avg critic losses: tensor(7.3707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1913 - Score: 0.10000000149 Avg critic losses: tensor(7.8877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) episode done in 53 time steps; scores: [ 0.09 0.1 ] Episode 1914 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1915 - Score: 0.10000000149 Avg critic losses: tensor(9.8340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0300, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0308, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0278, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1916 - Score: 0.10000000149 Avg critic losses: tensor(8.0935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0292, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) episode done in 33 time steps; scores: [ 0.1 -0.01] Episode 1917 - Score: 0.10000000149 Avg critic losses: tensor(7.5588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1918 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0307, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.1 0.09] Episode 1919 - Score: 0.10000000149 Avg critic losses: tensor(7.9710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 1920 - Score: 0.20000000298 Episode 1920 - Mean score: 0.110400001667 Avg critic losses: tensor(6.2343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1921 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1922 - Score: 0.10000000149 Avg critic losses: tensor(7.6271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0299, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0287, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1923 - Score: 0.10000000149 Avg critic losses: tensor(8.4384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) episode done in 70 time steps; scores: [ 0.1 0.09] Episode 1924 - Score: 0.10000000149 Avg critic losses: tensor(6.7088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0285, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1925 - Score: 0.10000000149 Avg critic losses: tensor(6.8910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1926 - Score: 0.10000000149 Avg critic losses: tensor(6.1380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1927 - Score: 0.10000000149 Avg critic losses: tensor(7.6554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0316, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.1 0.19] Episode 1928 - Score: 0.190000003204 Avg critic losses: tensor(5.6701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 1929 - Score: 0.20000000298 Avg critic losses: tensor(9.9831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1930 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 1931 - Score: 0.190000003204 Avg critic losses: tensor(6.2245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1932 - Score: 0.10000000149 Avg critic losses: tensor(6.9164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1933 - Score: 0.10000000149 Avg critic losses: tensor(7.2756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1934 - Score: 0.10000000149 Avg critic losses: tensor(7.1952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.1 0.09] Episode 1935 - Score: 0.10000000149 Avg critic losses: tensor(6.5955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1936 - Score: 0.10000000149 Avg critic losses: tensor(6.6278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1937 - Score: 0.10000000149 Avg critic losses: tensor(6.9875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1938 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1939 - Score: 0.10000000149 Avg critic losses: tensor(8.3767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1940 - Score: 0.10000000149 Episode 1940 - Mean score: 0.113300001714 Avg critic losses: tensor(6.3939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1941 - Score: 0.10000000149 Avg critic losses: tensor(9.1038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1942 - Score: 0.10000000149 Avg critic losses: tensor(7.6865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1943 - Score: 0.10000000149 Avg critic losses: tensor(8.6052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0320, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1944 - Score: 0.10000000149 Avg critic losses: tensor(6.1754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) episode done in 34 time steps; scores: [-0.01 0.1 ] Episode 1945 - Score: 0.10000000149 Avg critic losses: tensor(7.7769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1946 - Score: 0.10000000149 Avg critic losses: tensor(9.1019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1947 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1948 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1949 - Score: 0.10000000149 Avg critic losses: tensor(8.0811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1950 - Score: 0.10000000149 Avg critic losses: tensor(7.9485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1951 - Score: 0.10000000149 Avg critic losses: tensor(8.2533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1952 - Score: 0.10000000149 Avg critic losses: tensor(7.7604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1953 - Score: 0.10000000149 Avg critic losses: tensor(9.2330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1954 - Score: 0.10000000149 Avg critic losses: tensor(8.6507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1955 - Score: 0.10000000149 Avg critic losses: tensor(7.3195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 1956 - Score: 0.10000000149 Avg critic losses: tensor(7.7383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1957 - Score: 0.10000000149 Avg critic losses: tensor(8.2651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1958 - Score: 0.10000000149 Avg critic losses: tensor(6.8866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) episode done in 32 time steps; scores: [-0.01 0.1 ] Episode 1959 - Score: 0.10000000149 Avg critic losses: tensor(6.1167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1960 - Score: 0.10000000149 Episode 1960 - Mean score: 0.113400001712 Avg critic losses: tensor(5.8305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 0.09] Episode 1961 - Score: 0.10000000149 Avg critic losses: tensor(9.6431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0312, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0. ] Episode 1962 - Score: 0.0 Avg critic losses: tensor(8.3359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0313, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1963 - Score: 0.10000000149 Avg critic losses: tensor(8.3018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) episode done in 32 time steps; scores: [ 0.1 -0.01] Episode 1964 - Score: 0.10000000149 Avg critic losses: tensor(9.5756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.1 0.19] Episode 1965 - Score: 0.190000003204 Avg critic losses: tensor(5.2317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1966 - Score: 0.0900000017136 Avg critic losses: tensor(7.5371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1967 - Score: 0.10000000149 Avg critic losses: tensor(7.6720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1968 - Score: 0.10000000149 Avg critic losses: tensor(6.7061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1969 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1970 - Score: 0.10000000149 Avg critic losses: tensor(7.8285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 1971 - Score: 0.0900000017136 Avg critic losses: tensor(5.3264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [-0.01 0.1 ] Episode 1972 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0314, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0324, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0286, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1973 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0311, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1974 - Score: 0.10000000149 Avg critic losses: tensor(6.2951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1975 - Score: 0.10000000149 Avg critic losses: tensor(8.1100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1976 - Score: 0.0900000017136 Avg critic losses: tensor(7.4543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1977 - Score: 0.10000000149 Avg critic losses: tensor(6.9376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0322, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1978 - Score: 0.10000000149 Avg critic losses: tensor(8.1353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) episode done in 68 time steps; scores: [ 0.09 0.2 ] Episode 1979 - Score: 0.20000000298 Avg critic losses: tensor(6.2622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1980 - Score: 0.10000000149 Episode 1980 - Mean score: 0.110000001676 Avg critic losses: tensor(8.2222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) episode done in 53 time steps; scores: [ 0.1 0.09] Episode 1981 - Score: 0.10000000149 Avg critic losses: tensor(8.7324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [ 0. -0.01] Episode 1982 - Score: 0.0 Avg critic losses: tensor(6.1536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) episode done in 32 time steps; scores: [ 0.1 -0.01] Episode 1983 - Score: 0.10000000149 Avg critic losses: tensor(8.6684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.1 0.19] Episode 1984 - Score: 0.190000003204 Avg critic losses: tensor(5.2205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1985 - Score: 0.10000000149 Avg critic losses: tensor(9.5107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1986 - Score: 0.10000000149 Avg critic losses: tensor(5.4149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 1987 - Score: 0.0900000017136 Avg critic losses: tensor(9.9027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1988 - Score: 0.10000000149 Avg critic losses: tensor(5.2567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.09 0.1 ] Episode 1989 - Score: 0.10000000149 Avg critic losses: tensor(9.6893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1990 - Score: 0.10000000149 Avg critic losses: tensor(8.3692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 1991 - Score: 0.10000000149 Avg critic losses: tensor(6.4549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1992 - Score: 0.10000000149 Avg critic losses: tensor(8.2766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 1993 - Score: 0.10000000149 Avg critic losses: tensor(9.2276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 0.09] Episode 1994 - Score: 0.10000000149 Avg critic losses: tensor(6.9083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1995 - Score: 0.10000000149 Avg critic losses: tensor(5.0548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1996 - Score: 0.10000000149 Avg critic losses: tensor(9.0678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 1997 - Score: 0.10000000149 Avg critic losses: tensor(7.8561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 1998 - Score: 0.10000000149 Avg critic losses: tensor(9.2714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.09] Episode 1999 - Score: 0.10000000149 Avg critic losses: tensor(9.4353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0301, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.1 -0.01] Episode 2000 - Score: 0.10000000149 Episode 2000 - Mean score: 0.106000001617 Avg critic losses: tensor(7.2544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2001 - Score: 0.10000000149 Avg critic losses: tensor(7.9558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2002 - Score: 0.10000000149 Avg critic losses: tensor(6.6658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2003 - Score: 0.10000000149 Avg critic losses: tensor(6.3551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2004 - Score: 0.10000000149 Avg critic losses: tensor(5.9038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2005 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2006 - Score: 0.10000000149 Avg critic losses: tensor(8.0253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2007 - Score: 0.10000000149 Avg critic losses: tensor(5.0498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2008 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2009 - Score: 0.10000000149 Avg critic losses: tensor(4.8586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2010 - Score: 0.10000000149 Avg critic losses: tensor(8.0929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0332, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) episode done in 53 time steps; scores: [ 0.1 0.09] Episode 2011 - Score: 0.10000000149 Avg critic losses: tensor(6.8112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2012 - Score: 0.10000000149 Avg critic losses: tensor(6.1558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2013 - Score: 0.190000003204 Avg critic losses: tensor(7.2157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2014 - Score: 0.0900000017136 Avg critic losses: tensor(8.0486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) episode done in 13 time steps; scores: [ 0. -0.01] Episode 2015 - Score: 0.0 Avg critic losses: tensor(7.7297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0338, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2016 - Score: 0.10000000149 Avg critic losses: tensor(9.3321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2017 - Score: 0.10000000149 Avg critic losses: tensor(7.6710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2018 - Score: 0.10000000149 Avg critic losses: tensor(6.0141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2019 - Score: 0.10000000149 Avg critic losses: tensor(8.0855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2020 - Score: 0.20000000298 Episode 2020 - Mean score: 0.103900001589 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0318, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) episode done in 65 time steps; scores: [ 0.1 0.19] Episode 2021 - Score: 0.190000003204 Avg critic losses: tensor(7.6302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.09 0.1 ] Episode 2022 - Score: 0.10000000149 Avg critic losses: tensor(8.5591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2023 - Score: 0.20000000298 Avg critic losses: tensor(8.2281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0327, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.09 0.1 ] Episode 2024 - Score: 0.10000000149 Avg critic losses: tensor(7.2571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2025 - Score: 0.190000003204 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2026 - Score: 0.10000000149 Avg critic losses: tensor(8.5169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2027 - Score: 0.10000000149 Avg critic losses: tensor(5.2450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.09 0.1 ] Episode 2028 - Score: 0.10000000149 Avg critic losses: tensor(7.2419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.6127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.1 0.19] Episode 2029 - Score: 0.190000003204 Avg critic losses: tensor(8.6517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 2030 - Score: 0.20000000298 Avg critic losses: tensor(9.9489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0317, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.09 0.1 ] Episode 2031 - Score: 0.10000000149 Avg critic losses: tensor(7.1210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2032 - Score: 0.10000000149 Avg critic losses: tensor(7.6388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0333, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) episode done in 55 time steps; scores: [ 0.1 0.09] Episode 2033 - Score: 0.10000000149 Avg critic losses: tensor(8.4071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2034 - Score: 0.10000000149 Avg critic losses: tensor(8.7814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2035 - Score: 0.20000000298 Avg critic losses: tensor(6.0518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2036 - Score: 0.10000000149 Avg critic losses: tensor(8.5727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2037 - Score: 0.10000000149 Avg critic losses: tensor(6.3021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0323, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2038 - Score: 0.10000000149 Avg critic losses: tensor(7.5920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 2039 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.7913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2040 - Score: 0.0900000017136 Episode 2040 - Mean score: 0.107700001653 Avg critic losses: tensor(9.8892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0331, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2041 - Score: 0.190000003204 Avg critic losses: tensor(8.2173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) episode done in 42 time steps; scores: [-0.01 0.1 ] Episode 2042 - Score: 0.10000000149 Avg critic losses: tensor(8.7224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2043 - Score: 0.10000000149 Avg critic losses: tensor(6.8010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2044 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2045 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2046 - Score: 0.0900000017136 Avg critic losses: tensor(8.7110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2047 - Score: 0.10000000149 Avg critic losses: tensor(5.9350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0315, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0343, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) episode done in 69 time steps; scores: [ 0.2 0.09] Episode 2048 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2049 - Score: 0.190000003204 Avg critic losses: tensor(7.0287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0337, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0328, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2050 - Score: 0.10000000149 Avg critic losses: tensor(6.8667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0339, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0344, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) episode done in 32 time steps; scores: [ 0.1 -0.01] Episode 2051 - Score: 0.10000000149 Avg critic losses: tensor(9.9496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2052 - Score: 0.10000000149 Avg critic losses: tensor(8.8279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.09 0.1 ] Episode 2053 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) episode done in 65 time steps; scores: [ 0.2 0.09] Episode 2054 - Score: 0.20000000298 Avg critic losses: tensor(9.5294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2055 - Score: 0.20000000298 Avg critic losses: tensor(8.1925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2056 - Score: 0.10000000149 Avg critic losses: tensor(5.5265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2057 - Score: 0.20000000298 Avg critic losses: tensor(8.4807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0321, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2058 - Score: 0.20000000298 Avg critic losses: tensor(8.7312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2059 - Score: 0.10000000149 Avg critic losses: tensor(7.0809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2060 - Score: 0.10000000149 Episode 2060 - Mean score: 0.114300001767 Avg critic losses: tensor(5.7798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2061 - Score: 0.20000000298 Avg critic losses: tensor(9.4337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) episode done in 41 time steps; scores: [-0.01 0.1 ] Episode 2062 - Score: 0.10000000149 Avg critic losses: tensor(7.7187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2063 - Score: 0.10000000149 Avg critic losses: tensor(6.6776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0303, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2064 - Score: 0.190000003204 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2065 - Score: 0.10000000149 Avg critic losses: tensor(8.0310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2066 - Score: 0.10000000149 Avg critic losses: tensor(9.3175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0342, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2067 - Score: 0.10000000149 Avg critic losses: tensor(7.1503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0326, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0357, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0335, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0340, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2068 - Score: 0.20000000298 Avg critic losses: tensor(7.3162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2069 - Score: 0.10000000149 Avg critic losses: tensor(8.7337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2070 - Score: 0.10000000149 Avg critic losses: tensor(6.7458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) episode done in 70 time steps; scores: [ 0.1 0.09] Episode 2071 - Score: 0.10000000149 Avg critic losses: tensor(8.1166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0329, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2072 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2073 - Score: 0.10000000149 Avg critic losses: tensor(6.6970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2074 - Score: 0.10000000149 Avg critic losses: tensor(4.6456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2075 - Score: 0.0900000017136 Avg critic losses: tensor(6.6547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) episode done in 40 time steps; scores: [-0.01 0.1 ] Episode 2076 - Score: 0.10000000149 Avg critic losses: tensor(5.6049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0336, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2077 - Score: 0.0900000017136 Avg critic losses: tensor(9.0443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0.1 -0.01] Episode 2078 - Score: 0.10000000149 Avg critic losses: tensor(8.1294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0334, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2079 - Score: 0.190000003204 Avg critic losses: tensor(9.5265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2080 - Score: 0.10000000149 Episode 2080 - Mean score: 0.117400001809 Avg critic losses: tensor(6.2850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) episode done in 35 time steps; scores: [ 0.1 -0.01] Episode 2081 - Score: 0.10000000149 Avg critic losses: tensor(6.5482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) episode done in 81 time steps; scores: [ 0.09 0.2 ] Episode 2082 - Score: 0.20000000298 Avg critic losses: tensor(7.2966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0319, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0347, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.1 0.09] Episode 2083 - Score: 0.10000000149 Avg critic losses: tensor(9.6508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2084 - Score: 0.10000000149 Avg critic losses: tensor(7.1117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0351, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) episode done in 68 time steps; scores: [ 0.2 0.09] Episode 2085 - Score: 0.20000000298 Avg critic losses: tensor(9.1110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) episode done in 68 time steps; scores: [ 0.2 0.09] Episode 2086 - Score: 0.20000000298 Avg critic losses: tensor(8.3687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0348, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0346, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) episode done in 65 time steps; scores: [ 0.1 0.19] Episode 2087 - Score: 0.190000003204 Avg critic losses: tensor(6.3925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2088 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0. 0.09] Episode 2089 - Score: 0.0900000017136 Avg critic losses: tensor(9.6791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0.1 -0.01] Episode 2090 - Score: 0.10000000149 Avg critic losses: tensor(9.5332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2091 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0330, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 2092 - Score: 0.20000000298 Avg critic losses: tensor(7.7306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2093 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [ 0.1 -0.01] Episode 2094 - Score: 0.10000000149 Avg critic losses: tensor(6.5817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2095 - Score: 0.0900000017136 Avg critic losses: tensor(8.2623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2096 - Score: 0.10000000149 Avg critic losses: tensor(6.1896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2097 - Score: 0.0900000017136 Avg critic losses: tensor(9.9090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0353, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2098 - Score: 0.0900000017136 Avg critic losses: tensor(9.7293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2099 - Score: 0.10000000149 Avg critic losses: tensor(7.1638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2100 - Score: 0.10000000149 Episode 2100 - Mean score: 0.12210000189 Avg critic losses: tensor(7.3681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2101 - Score: 0.10000000149 Avg critic losses: tensor(6.0360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0354, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2102 - Score: 0.10000000149 Avg critic losses: tensor(7.8264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2103 - Score: 0.10000000149 Avg critic losses: tensor(6.7676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2104 - Score: 0.10000000149 Avg critic losses: tensor(7.4212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) episode done in 55 time steps; scores: [ 0.09 0.1 ] Episode 2105 - Score: 0.10000000149 Avg critic losses: tensor(6.7646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2106 - Score: 0.10000000149 Avg critic losses: tensor(7.0862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2107 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2108 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2109 - Score: 0.10000000149 Avg critic losses: tensor(9.3256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2110 - Score: 0.10000000149 Avg critic losses: tensor(6.9052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2111 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2112 - Score: 0.10000000149 Avg critic losses: tensor(7.0029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2113 - Score: 0.10000000149 Avg critic losses: tensor(7.2279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2114 - Score: 0.10000000149 Avg critic losses: tensor(8.2195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0352, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2115 - Score: 0.10000000149 Avg critic losses: tensor(9.7356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2116 - Score: 0.10000000149 Avg critic losses: tensor(9.1137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2117 - Score: 0.10000000149 Avg critic losses: tensor(7.0805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2118 - Score: 0.0900000017136 Avg critic losses: tensor(7.3104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2119 - Score: 0.10000000149 Avg critic losses: tensor(9.9321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2120 - Score: 0.10000000149 Episode 2120 - Mean score: 0.121100001875 Avg critic losses: tensor(9.9734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2121 - Score: 0.10000000149 Avg critic losses: tensor(7.7332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2122 - Score: 0.10000000149 Avg critic losses: tensor(7.6101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) episode done in 65 time steps; scores: [ 0.1 0.19] Episode 2123 - Score: 0.190000003204 Avg critic losses: tensor(8.6016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0345, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2124 - Score: 0.10000000149 Avg critic losses: tensor(8.0704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0350, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2125 - Score: 0.0900000017136 Avg critic losses: tensor(7.0437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0363, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2126 - Score: 0.10000000149 Avg critic losses: tensor(8.6417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2127 - Score: 0.10000000149 Avg critic losses: tensor(6.8705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2128 - Score: 0.10000000149 Avg critic losses: tensor(6.6479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2129 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2130 - Score: 0.10000000149 Avg critic losses: tensor(6.3255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2131 - Score: 0.0900000017136 Avg critic losses: tensor(8.7827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0364, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 -0.01] Episode 2132 - Score: 0.10000000149 Avg critic losses: tensor(7.3020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2133 - Score: 0.10000000149 Avg critic losses: tensor(6.2348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2134 - Score: 0.10000000149 Avg critic losses: tensor(8.0412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.5144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2135 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2136 - Score: 0.10000000149 Avg critic losses: tensor(6.7667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2137 - Score: 0.10000000149 Avg critic losses: tensor(7.1497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2138 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) episode done in 48 time steps; scores: [-0.01 0.1 ] Episode 2139 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0349, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0325, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2140 - Score: 0.10000000149 Episode 2140 - Mean score: 0.115100001786 Avg critic losses: tensor(9.1695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0341, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0356, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2141 - Score: 0.10000000149 Avg critic losses: tensor(7.0743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2142 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2143 - Score: 0.10000000149 Avg critic losses: tensor(8.2806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2144 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2145 - Score: 0.10000000149 Avg critic losses: tensor(9.0729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2146 - Score: 0.10000000149 Avg critic losses: tensor(8.4009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2147 - Score: 0.10000000149 Avg critic losses: tensor(8.2020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0355, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2148 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0366, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) episode done in 85 time steps; scores: [ 0.2 0.09] Episode 2149 - Score: 0.20000000298 Avg critic losses: tensor(7.7208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2150 - Score: 0.0900000017136 Avg critic losses: tensor(9.5793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2151 - Score: 0.0900000017136 Avg critic losses: tensor(6.3296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) episode done in 46 time steps; scores: [-0.01 0.1 ] Episode 2152 - Score: 0.10000000149 Avg critic losses: tensor(7.4106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2153 - Score: 0.10000000149 Avg critic losses: tensor(8.9982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2154 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) episode done in 69 time steps; scores: [ 0.09 0.2 ] Episode 2155 - Score: 0.20000000298 Avg critic losses: tensor(9.0568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2156 - Score: 0.10000000149 Avg critic losses: tensor(6.3241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2157 - Score: 0.10000000149 Avg critic losses: tensor(9.4736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) episode done in 70 time steps; scores: [ 0.2 0.09] Episode 2158 - Score: 0.20000000298 Avg critic losses: tensor(8.9330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2159 - Score: 0.10000000149 Avg critic losses: tensor(9.0826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2160 - Score: 0.0900000017136 Episode 2160 - Mean score: 0.111100001726 Avg critic losses: tensor(9.6628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2161 - Score: 0.10000000149 Avg critic losses: tensor(7.2070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2162 - Score: 0.10000000149 Avg critic losses: tensor(5.4405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2163 - Score: 0.0900000017136 Avg critic losses: tensor(9.3851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0362, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2164 - Score: 0.10000000149 Avg critic losses: tensor(6.3215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2165 - Score: 0.10000000149 Avg critic losses: tensor(6.0868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0359, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2166 - Score: 0.0900000017136 Avg critic losses: tensor(9.4728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0371, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2167 - Score: 0.0900000017136 Avg critic losses: tensor(6.6819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2168 - Score: 0.0900000017136 Avg critic losses: tensor(7.3008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0360, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2169 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2170 - Score: 0.10000000149 Avg critic losses: tensor(7.8493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2171 - Score: 0.0900000017136 Avg critic losses: tensor(7.2770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2172 - Score: 0.0900000017136 Avg critic losses: tensor(9.0069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2173 - Score: 0.10000000149 Avg critic losses: tensor(6.1029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2174 - Score: 0.0900000017136 Avg critic losses: tensor(6.7119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0361, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2175 - Score: 0.0900000017136 Avg critic losses: tensor(7.4421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0383, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2176 - Score: 0.10000000149 Avg critic losses: tensor(7.7376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2177 - Score: 0.0900000017136 Avg critic losses: tensor(7.8384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0368, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0365, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0376, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0378, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2178 - Score: 0.10000000149 Avg critic losses: tensor(8.3939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0373, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0385, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2179 - Score: 0.10000000149 Avg critic losses: tensor(7.4313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0372, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2180 - Score: 0.0900000017136 Episode 2180 - Mean score: 0.10650000168 Avg critic losses: tensor(9.3818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [-0.01 0.1 ] Episode 2181 - Score: 0.10000000149 Avg critic losses: tensor(6.6849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0375, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2182 - Score: 0.10000000149 Avg critic losses: tensor(9.2021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2183 - Score: 0.10000000149 Avg critic losses: tensor(7.0908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2184 - Score: 0.10000000149 Avg critic losses: tensor(8.1680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2185 - Score: 0.0900000017136 Avg critic losses: tensor(9.1354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2186 - Score: 0.10000000149 Avg critic losses: tensor(8.8965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0389, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) episode done in 68 time steps; scores: [ 0.2 0.09] Episode 2187 - Score: 0.20000000298 Avg critic losses: tensor(8.2734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2188 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0377, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0369, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2189 - Score: 0.10000000149 Avg critic losses: tensor(6.4326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2190 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0397, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) episode done in 109 time steps; scores: [ 0.09 0.2 ] Episode 2191 - Score: 0.20000000298 Avg critic losses: tensor(7.1000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0381, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2192 - Score: 0.0900000017136 Avg critic losses: tensor(8.4830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0374, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0392, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.1 0.09] Episode 2193 - Score: 0.10000000149 Avg critic losses: tensor(8.7175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0370, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) episode done in 68 time steps; scores: [ 0.09 0.2 ] Episode 2194 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0391, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2195 - Score: 0.0900000017136 Avg critic losses: tensor(6.0051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) episode done in 42 time steps; scores: [-0.01 0.1 ] Episode 2196 - Score: 0.10000000149 Avg critic losses: tensor(6.9017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2197 - Score: 0.0900000017136 Avg critic losses: tensor(9.8507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2198 - Score: 0.10000000149 Avg critic losses: tensor(7.8425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0379, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2199 - Score: 0.0900000017136 Avg critic losses: tensor(6.6810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2200 - Score: 0.10000000149 Episode 2200 - Mean score: 0.104400001653 Avg critic losses: tensor(8.6747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) episode done in 53 time steps; scores: [ 0.1 0.09] Episode 2201 - Score: 0.10000000149 Avg critic losses: tensor(9.5058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2202 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0390, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0358, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2203 - Score: 0.190000003204 Avg critic losses: tensor(9.5460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0399, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0386, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) episode done in 43 time steps; scores: [ 0.1 -0.01] Episode 2204 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [ 0. 0.09] Episode 2205 - Score: 0.0900000017136 Avg critic losses: tensor(7.1642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2206 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2207 - Score: 0.0900000017136 Avg critic losses: tensor(6.5291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0388, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) episode done in 62 time steps; scores: [ 0.1 0.09] Episode 2208 - Score: 0.10000000149 Avg critic losses: tensor(9.3718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2209 - Score: 0.0900000017136 Avg critic losses: tensor(8.4203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2210 - Score: 0.0900000017136 Avg critic losses: tensor(7.2804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2211 - Score: 0.10000000149 Avg critic losses: tensor(8.1300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0395, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2212 - Score: 0.10000000149 Avg critic losses: tensor(9.9697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0404, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2213 - Score: 0.10000000149 Avg critic losses: tensor(8.4832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [ 0. 0.09] Episode 2214 - Score: 0.0900000017136 Avg critic losses: tensor(9.5259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2215 - Score: 0.10000000149 Avg critic losses: tensor(7.0374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0414, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2216 - Score: 0.0900000017136 Avg critic losses: tensor(6.3436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0401, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2217 - Score: 0.10000000149 Avg critic losses: tensor(6.5938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) episode done in 56 time steps; scores: [ 0.1 0.09] Episode 2218 - Score: 0.10000000149 Avg critic losses: tensor(7.6882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.1 0.09] Episode 2219 - Score: 0.10000000149 Avg critic losses: tensor(7.3446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0419, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2220 - Score: 0.0900000017136 Episode 2220 - Mean score: 0.104800001681 Avg critic losses: tensor(9.7349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2221 - Score: 0.0900000017136 Avg critic losses: tensor(7.4627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) episode done in 18 time steps; scores: [ 0.09 0. ] Episode 2222 - Score: 0.0900000035763 Avg critic losses: tensor(6.7436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0410, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) episode done in 53 time steps; scores: [ 0.09 0.1 ] Episode 2223 - Score: 0.10000000149 Avg critic losses: tensor(7.5422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0412, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0403, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0384, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [-0.01 0.1 ] Episode 2224 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0393, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2225 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0407, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0405, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0424, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0398, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2226 - Score: 0.10000000149 Avg critic losses: tensor(8.8991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0406, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0402, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2227 - Score: 0.10000000149 Avg critic losses: tensor(6.4898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2228 - Score: 0.0900000017136 Avg critic losses: tensor(5.9518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0382, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) episode done in 53 time steps; scores: [ 0.1 0.09] Episode 2229 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0367, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2230 - Score: 0.10000000149 Avg critic losses: tensor(7.3100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2231 - Score: 0.10000000149 Avg critic losses: tensor(8.1403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2232 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2233 - Score: 0.0900000017136 Avg critic losses: tensor(9.9880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2234 - Score: 0.0900000017136 Avg critic losses: tensor(9.3233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2235 - Score: 0.10000000149 Avg critic losses: tensor(7.1754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) episode done in 55 time steps; scores: [ 0.09 0.1 ] Episode 2236 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0411, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.1 0.09] Episode 2237 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2238 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0408, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2239 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2240 - Score: 0.0900000017136 Episode 2240 - Mean score: 0.103600001689 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0418, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [-0.01 0.1 ] Episode 2241 - Score: 0.10000000149 Avg critic losses: tensor(8.1544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2242 - Score: 0.10000000149 Avg critic losses: tensor(9.8640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2243 - Score: 0.0900000017136 Avg critic losses: tensor(7.5362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0394, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0422, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2244 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [-0.01 0.1 ] Episode 2245 - Score: 0.10000000149 Avg critic losses: tensor(4.3716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2246 - Score: 0.10000000149 Avg critic losses: tensor(8.2121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0409, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2247 - Score: 0.10000000149 Avg critic losses: tensor(9.4536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2248 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2249 - Score: 0.10000000149 Avg critic losses: tensor(6.7444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2250 - Score: 0.0900000017136 Avg critic losses: tensor(9.1633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 0.09] Episode 2251 - Score: 0.10000000149 Avg critic losses: tensor(8.9452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2252 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2253 - Score: 0.10000000149 Avg critic losses: tensor(9.5099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2254 - Score: 0.10000000149 Avg critic losses: tensor(6.8669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2255 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0387, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [-0.01 0.1 ] Episode 2256 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0619, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0380, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2257 - Score: 0.10000000149 Avg critic losses: tensor(9.8450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2258 - Score: 0.10000000149 Avg critic losses: tensor(9.6813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0425, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2259 - Score: 0.10000000149 Avg critic losses: tensor(8.3642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [-0.01 0.1 ] Episode 2260 - Score: 0.10000000149 Episode 2260 - Mean score: 0.10080000164 Avg critic losses: tensor(7.2059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) episode done in 68 time steps; scores: [ 0.1 0.19] Episode 2261 - Score: 0.190000003204 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2262 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2263 - Score: 0.0900000017136 Avg critic losses: tensor(9.6323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2264 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0415, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) episode done in 108 time steps; scores: [ 0.2 0.19] Episode 2265 - Score: 0.20000000298 Avg critic losses: tensor(8.5446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2266 - Score: 0.0900000017136 Avg critic losses: tensor(8.0860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) episode done in 53 time steps; scores: [ 0.1 0.09] Episode 2267 - Score: 0.10000000149 Avg critic losses: tensor(9.6493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2268 - Score: 0.10000000149 Avg critic losses: tensor(9.4972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) episode done in 65 time steps; scores: [ 0.1 -0.01] Episode 2269 - Score: 0.10000000149 Avg critic losses: tensor(9.4958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2270 - Score: 0.190000003204 Avg critic losses: tensor(9.8033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) episode done in 43 time steps; scores: [ 0.1 -0.01] Episode 2271 - Score: 0.10000000149 Avg critic losses: tensor(6.3989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0430, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.09 0.1 ] Episode 2272 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2273 - Score: 0.0900000017136 Avg critic losses: tensor(8.5485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0610, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2274 - Score: 0.10000000149 Avg critic losses: tensor(7.8907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0416, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2275 - Score: 0.10000000149 Avg critic losses: tensor(7.5422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 2276 - Score: 0.20000000298 Avg critic losses: tensor(7.5845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) episode done in 64 time steps; scores: [ 0.1 0.09] Episode 2277 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 0.09] Episode 2278 - Score: 0.10000000149 Avg critic losses: tensor(8.9058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) episode done in 32 time steps; scores: [-0.01 0.1 ] Episode 2279 - Score: 0.10000000149 Avg critic losses: tensor(7.8913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0421, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [-0.01 0.1 ] Episode 2280 - Score: 0.10000000149 Episode 2280 - Mean score: 0.105300001688 Avg critic losses: tensor(6.7001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2281 - Score: 0.10000000149 Avg critic losses: tensor(8.7111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2282 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2283 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2284 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2285 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2286 - Score: 0.0900000017136 Avg critic losses: tensor(5.2415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2287 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2288 - Score: 0.0900000017136 Avg critic losses: tensor(8.5929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2289 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2290 - Score: 0.10000000149 Avg critic losses: tensor(9.2939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) episode done in 62 time steps; scores: [ 0.1 0.09] Episode 2291 - Score: 0.10000000149 Avg critic losses: tensor(7.0531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) episode done in 63 time steps; scores: [ 0.09 0.1 ] Episode 2292 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.09 0.1 ] Episode 2293 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2294 - Score: 0.10000000149 Avg critic losses: tensor(8.2028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2295 - Score: 0.10000000149 Avg critic losses: tensor(8.8704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2296 - Score: 0.10000000149 Avg critic losses: tensor(4.9701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0.1 -0.01] Episode 2297 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.09 0.1 ] Episode 2298 - Score: 0.10000000149 Avg critic losses: tensor(6.8961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0400, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2299 - Score: 0.10000000149 Avg critic losses: tensor(8.8704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2300 - Score: 0.10000000149 Episode 2300 - Mean score: 0.102400001641 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2301 - Score: 0.0900000017136 Avg critic losses: tensor(7.2422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2302 - Score: 0.0900000017136 Avg critic losses: tensor(7.7607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2303 - Score: 0.0900000017136 Avg critic losses: tensor(8.8102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [-0.01 0.1 ] Episode 2304 - Score: 0.10000000149 Avg critic losses: tensor(8.3638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) episode done in 53 time steps; scores: [ 0.1 0.09] Episode 2305 - Score: 0.10000000149 Avg critic losses: tensor(8.7327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) episode done in 69 time steps; scores: [ 0.2 0.09] Episode 2306 - Score: 0.20000000298 Avg critic losses: tensor(8.4064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2307 - Score: 0.10000000149 Avg critic losses: tensor(7.4953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2308 - Score: 0.10000000149 Avg critic losses: tensor(9.4549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) episode done in 56 time steps; scores: [ 0.09 0.1 ] Episode 2309 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) episode done in 49 time steps; scores: [ 0.1 -0.01] Episode 2310 - Score: 0.10000000149 Avg critic losses: tensor(8.7678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) episode done in 90 time steps; scores: [ 0.2 0.09] Episode 2311 - Score: 0.20000000298 Avg critic losses: tensor(7.3546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) episode done in 65 time steps; scores: [ 0.2 0.09] Episode 2312 - Score: 0.20000000298 Avg critic losses: tensor(6.8159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2313 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 2314 - Score: 0.20000000298 Avg critic losses: tensor(7.3786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2315 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) episode done in 48 time steps; scores: [-0.01 0.1 ] Episode 2316 - Score: 0.10000000149 Avg critic losses: tensor(9.9128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0420, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2317 - Score: 0.10000000149 Avg critic losses: tensor(9.0240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2318 - Score: 0.10000000149 Avg critic losses: tensor(8.1646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2319 - Score: 0.0900000017136 Avg critic losses: tensor(6.0802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) episode done in 53 time steps; scores: [ 0.1 0.09] Episode 2320 - Score: 0.10000000149 Episode 2320 - Mean score: 0.105700001679 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2321 - Score: 0.10000000149 Avg critic losses: tensor(8.1956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2322 - Score: 0.10000000149 Avg critic losses: tensor(8.3635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0436, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2323 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2324 - Score: 0.10000000149 Avg critic losses: tensor(9.0250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2325 - Score: 0.10000000149 Avg critic losses: tensor(7.2466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0423, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2326 - Score: 0.10000000149 Avg critic losses: tensor(7.7276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2327 - Score: 0.0900000017136 Avg critic losses: tensor(6.1279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2328 - Score: 0.10000000149 Avg critic losses: tensor(6.7180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0428, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.09 0.1 ] Episode 2329 - Score: 0.10000000149 Avg critic losses: tensor(8.6451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2330 - Score: 0.10000000149 Avg critic losses: tensor(9.0673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2331 - Score: 0.0900000017136 Avg critic losses: tensor(9.9502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2332 - Score: 0.10000000149 Avg critic losses: tensor(8.2900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2333 - Score: 0.10000000149 Avg critic losses: tensor(6.9285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2334 - Score: 0.10000000149 Avg critic losses: tensor(9.9825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2335 - Score: 0.10000000149 Avg critic losses: tensor(8.2418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2336 - Score: 0.10000000149 Avg critic losses: tensor(7.3628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2337 - Score: 0.10000000149 Avg critic losses: tensor(7.1422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) episode done in 70 time steps; scores: [ 0.09 0.2 ] Episode 2338 - Score: 0.20000000298 Avg critic losses: tensor(6.5493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0613, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2339 - Score: 0.10000000149 Avg critic losses: tensor(8.2820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2340 - Score: 0.10000000149 Episode 2340 - Mean score: 0.107000001669 Avg critic losses: tensor(6.8168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2341 - Score: 0.10000000149 Avg critic losses: tensor(8.4465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2342 - Score: 0.10000000149 Avg critic losses: tensor(7.9204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2343 - Score: 0.10000000149 Avg critic losses: tensor(9.3151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2344 - Score: 0.10000000149 Avg critic losses: tensor(8.7187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) episode done in 48 time steps; scores: [ 0.2 -0.01] Episode 2345 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2346 - Score: 0.10000000149 Avg critic losses: tensor(8.8198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2347 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2348 - Score: 0.10000000149 Avg critic losses: tensor(7.7764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2349 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2350 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0.1 -0.01] Episode 2351 - Score: 0.10000000149 Avg critic losses: tensor(8.5669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) episode done in 125 time steps; scores: [ 0.29 0.3 ] Episode 2352 - Score: 0.30000000447 Avg critic losses: tensor(8.9387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2353 - Score: 0.190000003204 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2354 - Score: 0.10000000149 Avg critic losses: tensor(9.8257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2355 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2356 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2357 - Score: 0.10000000149 Avg critic losses: tensor(5.4128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2358 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 0.09] Episode 2359 - Score: 0.10000000149 Avg critic losses: tensor(9.2525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2360 - Score: 0.10000000149 Episode 2360 - Mean score: 0.111900001746 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 -0.01] Episode 2361 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2362 - Score: 0.0900000017136 Avg critic losses: tensor(9.7279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2363 - Score: 0.0900000017136 Avg critic losses: tensor(6.5218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2364 - Score: 0.10000000149 Avg critic losses: tensor(7.4282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2365 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2366 - Score: 0.10000000149 Avg critic losses: tensor(7.8800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 2367 - Score: 0.20000000298 Avg critic losses: tensor(6.6417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2368 - Score: 0.10000000149 Avg critic losses: tensor(7.9170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2369 - Score: 0.10000000149 Avg critic losses: tensor(8.7053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [-0.01 0.1 ] Episode 2370 - Score: 0.10000000149 Avg critic losses: tensor(7.6162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) episode done in 55 time steps; scores: [ 0.09 0.1 ] Episode 2371 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) episode done in 49 time steps; scores: [ 0.09 0.1 ] Episode 2372 - Score: 0.10000000149 Avg critic losses: tensor(6.4836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2373 - Score: 0.0900000017136 Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0619, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2374 - Score: 0.10000000149 Avg critic losses: tensor(8.3676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2375 - Score: 0.10000000149 Avg critic losses: tensor(9.4090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2376 - Score: 0.10000000149 Avg critic losses: tensor(7.6975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0617, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2377 - Score: 0.10000000149 Avg critic losses: tensor(7.4471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) episode done in 65 time steps; scores: [ 0.2 0.09] Episode 2378 - Score: 0.20000000298 Avg critic losses: tensor(8.2632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2379 - Score: 0.10000000149 Avg critic losses: tensor(8.4194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2380 - Score: 0.10000000149 Episode 2380 - Mean score: 0.110000001714 Avg critic losses: tensor(8.7388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2381 - Score: 0.20000000298 Avg critic losses: tensor(9.8794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) episode done in 48 time steps; scores: [ 0.1 -0.01] Episode 2382 - Score: 0.10000000149 Avg critic losses: tensor(7.0444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2383 - Score: 0.10000000149 Avg critic losses: tensor(7.3499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2384 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2385 - Score: 0.10000000149 Avg critic losses: tensor(8.6912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2386 - Score: 0.10000000149 Avg critic losses: tensor(7.8423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2387 - Score: 0.10000000149 Avg critic losses: tensor(7.6288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) episode done in 56 time steps; scores: [ 0.1 0.09] Episode 2388 - Score: 0.10000000149 Avg critic losses: tensor(7.6180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2389 - Score: 0.10000000149 Avg critic losses: tensor(6.2851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2390 - Score: 0.10000000149 Avg critic losses: tensor(8.6443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) episode done in 69 time steps; scores: [ 0.09 0.2 ] Episode 2391 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2392 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) episode done in 63 time steps; scores: [ 0.2 0.09] Episode 2393 - Score: 0.20000000298 Avg critic losses: tensor(6.7603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2394 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2395 - Score: 0.10000000149 Avg critic losses: tensor(7.7126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2396 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2397 - Score: 0.10000000149 Avg critic losses: tensor(7.3196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2398 - Score: 0.10000000149 Avg critic losses: tensor(8.5888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0413, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2399 - Score: 0.10000000149 Avg critic losses: tensor(8.2994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2400 - Score: 0.0900000017136 Episode 2400 - Mean score: 0.113300001752 Avg critic losses: tensor(9.1352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) episode done in 49 time steps; scores: [-0.01 0.1 ] Episode 2401 - Score: 0.10000000149 Avg critic losses: tensor(8.1138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.09 0.1 ] Episode 2402 - Score: 0.10000000149 Avg critic losses: tensor(9.8696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2403 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) episode done in 68 time steps; scores: [ 0.09 0.2 ] Episode 2404 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2405 - Score: 0.20000000298 Avg critic losses: tensor(6.6544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 2406 - Score: 0.20000000298 Avg critic losses: tensor(6.7991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2407 - Score: 0.10000000149 Avg critic losses: tensor(8.4631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2408 - Score: 0.10000000149 Avg critic losses: tensor(7.0382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2409 - Score: 0.20000000298 Avg critic losses: tensor(8.7593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2410 - Score: 0.10000000149 Avg critic losses: tensor(9.5807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2411 - Score: 0.10000000149 Avg critic losses: tensor(9.9288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2412 - Score: 0.10000000149 Avg critic losses: tensor(6.9945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2413 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2414 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [-0.01 0.1 ] Episode 2415 - Score: 0.10000000149 Avg critic losses: tensor(9.7431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.09 0.1 ] Episode 2416 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) episode done in 65 time steps; scores: [ 0.1 0.19] Episode 2417 - Score: 0.190000003204 Avg critic losses: tensor(8.8036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2418 - Score: 0.0900000017136 Avg critic losses: tensor(8.0220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.09 0.1 ] Episode 2419 - Score: 0.10000000149 Avg critic losses: tensor(6.2545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) episode done in 89 time steps; scores: [ 0.19 0.2 ] Episode 2420 - Score: 0.20000000298 Episode 2420 - Mean score: 0.115500001777 Avg critic losses: tensor(8.7326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2421 - Score: 0.190000003204 Avg critic losses: tensor(8.3311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0417, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) episode done in 57 time steps; scores: [ 0.1 0.09] Episode 2422 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2423 - Score: 0.10000000149 Avg critic losses: tensor(7.8793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2424 - Score: 0.10000000149 Avg critic losses: tensor(8.5339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2425 - Score: 0.10000000149 Avg critic losses: tensor(7.4161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) episode done in 55 time steps; scores: [ 0.1 0.09] Episode 2426 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.09 0.1 ] Episode 2427 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) episode done in 65 time steps; scores: [ 0.2 0.09] Episode 2428 - Score: 0.20000000298 Avg critic losses: tensor(7.6020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2429 - Score: 0.10000000149 Avg critic losses: tensor(8.5375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2430 - Score: 0.10000000149 Avg critic losses: tensor(9.2596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2431 - Score: 0.0900000017136 Avg critic losses: tensor(9.6691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2432 - Score: 0.10000000149 Avg critic losses: tensor(5.9304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2433 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) episode done in 57 time steps; scores: [ 0.09 0.1 ] Episode 2434 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0438, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2435 - Score: 0.10000000149 Avg critic losses: tensor(8.6162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2436 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2437 - Score: 0.10000000149 Avg critic losses: tensor(6.8971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2438 - Score: 0.190000003204 Avg critic losses: tensor(9.3145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2439 - Score: 0.0900000017136 Avg critic losses: tensor(9.8777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2440 - Score: 0.10000000149 Episode 2440 - Mean score: 0.117400001809 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0426, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.1 0.09] Episode 2441 - Score: 0.10000000149 Avg critic losses: tensor(8.4288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2442 - Score: 0.190000003204 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2443 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) episode done in 55 time steps; scores: [ 0.09 0.1 ] Episode 2444 - Score: 0.10000000149 Avg critic losses: tensor(7.7471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2445 - Score: 0.0900000017136 Avg critic losses: tensor(8.6605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0624, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) episode done in 164 time steps; scores: [ 0.39000001 0.40000001] Episode 2446 - Score: 0.40000000596 Avg critic losses: tensor(9.1648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2447 - Score: 0.10000000149 Avg critic losses: tensor(8.9570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0433, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0448, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.09 0.1 ] Episode 2448 - Score: 0.10000000149 Avg critic losses: tensor(9.3903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2449 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0622, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.09 0.1 ] Episode 2450 - Score: 0.10000000149 Avg critic losses: tensor(6.1018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2451 - Score: 0.10000000149 Avg critic losses: tensor(7.2130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0.1 -0.01] Episode 2452 - Score: 0.10000000149 Avg critic losses: tensor(8.3336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0614, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0. ] Episode 2453 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0635, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) episode done in 64 time steps; scores: [-0.01 0.1 ] Episode 2454 - Score: 0.10000000149 Avg critic losses: tensor(9.9875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2455 - Score: 0.10000000149 Avg critic losses: tensor(7.8658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) episode done in 55 time steps; scores: [ 0.09 0.1 ] Episode 2456 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0609, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2457 - Score: 0.0900000017136 Avg critic losses: tensor(8.2168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2458 - Score: 0.10000000149 Avg critic losses: tensor(7.0463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2459 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0622, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0437, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.09 0.1 ] Episode 2460 - Score: 0.10000000149 Episode 2460 - Mean score: 0.115300001781 Avg critic losses: tensor(7.0850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2461 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2462 - Score: 0.20000000298 Avg critic losses: tensor(9.1211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2463 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2464 - Score: 0.190000003204 Avg critic losses: tensor(9.8185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2465 - Score: 0.0900000017136 Avg critic losses: tensor(6.8654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) episode done in 90 time steps; scores: [ 0.19 0.2 ] Episode 2466 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(1.0000e-04, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0612, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.09 0.1 ] Episode 2467 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.09 0.1 ] Episode 2468 - Score: 0.10000000149 Avg critic losses: tensor(9.9481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0627, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0449, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.1 0.09] Episode 2469 - Score: 0.10000000149 Avg critic losses: tensor(7.4257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) episode done in 56 time steps; scores: [ 0.09 0.1 ] Episode 2470 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.09 0.1 ] Episode 2471 - Score: 0.10000000149 Avg critic losses: tensor(8.0841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) episode done in 55 time steps; scores: [ 0.1 0.09] Episode 2472 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2473 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2474 - Score: 0.190000003204 Avg critic losses: tensor(6.6928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0610, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2475 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) episode done in 56 time steps; scores: [ 0.09 0.1 ] Episode 2476 - Score: 0.10000000149 Avg critic losses: tensor(7.1424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2477 - Score: 0.10000000149 Avg critic losses: tensor(7.4627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2478 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2479 - Score: 0.0900000017136 Avg critic losses: tensor(9.6779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2480 - Score: 0.10000000149 Episode 2480 - Mean score: 0.118200001828 Avg critic losses: tensor(7.4444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) episode done in 70 time steps; scores: [ 0.09 0.2 ] Episode 2481 - Score: 0.20000000298 Avg critic losses: tensor(9.4046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.09 0.1 ] Episode 2482 - Score: 0.10000000149 Avg critic losses: tensor(8.5410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2483 - Score: 0.10000000149 Avg critic losses: tensor(8.4284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2484 - Score: 0.0900000017136 Avg critic losses: tensor(8.0082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0607, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2485 - Score: 0.10000000149 Avg critic losses: tensor(9.5859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.1 0.09] Episode 2486 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2487 - Score: 0.10000000149 Avg critic losses: tensor(6.9280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2488 - Score: 0.0900000017136 Avg critic losses: tensor(9.3265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2489 - Score: 0.10000000149 Avg critic losses: tensor(9.2507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0617, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.1 0.09] Episode 2490 - Score: 0.10000000149 Avg critic losses: tensor(7.6432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2491 - Score: 0.10000000149 Avg critic losses: tensor(9.9854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2492 - Score: 0.10000000149 Avg critic losses: tensor(7.9495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2493 - Score: 0.10000000149 Avg critic losses: tensor(8.7845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2494 - Score: 0.0900000017136 Avg critic losses: tensor(7.3058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) episode done in 32 time steps; scores: [-0.01 0.1 ] Episode 2495 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2496 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2497 - Score: 0.10000000149 Avg critic losses: tensor(8.3451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) episode done in 65 time steps; scores: [ 0.1 0.19] Episode 2498 - Score: 0.190000003204 Avg critic losses: tensor(6.0198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2499 - Score: 0.10000000149 Avg critic losses: tensor(7.3861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2500 - Score: 0.10000000149 Episode 2500 - Mean score: 0.117000001818 Avg critic losses: tensor(7.3626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.1 0.09] Episode 2501 - Score: 0.10000000149 Avg critic losses: tensor(6.2279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2502 - Score: 0.10000000149 Avg critic losses: tensor(7.0290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0620, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.1 0.19] Episode 2503 - Score: 0.190000003204 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0610, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) episode done in 65 time steps; scores: [ 0.2 0.09] Episode 2504 - Score: 0.20000000298 Avg critic losses: tensor(9.2005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) episode done in 107 time steps; scores: [ 0.19 0.3 ] Episode 2505 - Score: 0.30000000447 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2506 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.1 0.09] Episode 2507 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0439, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0618, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0440, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0444, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.1 0.09] Episode 2508 - Score: 0.10000000149 Avg critic losses: tensor(9.6405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) episode done in 56 time steps; scores: [ 0.1 0.09] Episode 2509 - Score: 0.10000000149 Avg critic losses: tensor(9.8007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0611, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0427, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) episode done in 65 time steps; scores: [ 0.2 0.09] Episode 2510 - Score: 0.20000000298 Avg critic losses: tensor(7.2842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 2511 - Score: 0.20000000298 Avg critic losses: tensor(8.6563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2512 - Score: 0.10000000149 Avg critic losses: tensor(7.5734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2513 - Score: 0.10000000149 Avg critic losses: tensor(7.8179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.1 0.09] Episode 2514 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0445, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2515 - Score: 0.10000000149 Avg critic losses: tensor(8.9702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0441, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0607, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0442, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 2516 - Score: 0.20000000298 Avg critic losses: tensor(7.0980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2517 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.09 0.1 ] Episode 2518 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0.1 -0.01] Episode 2519 - Score: 0.10000000149 Avg critic losses: tensor(8.8340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.1 0.09] Episode 2520 - Score: 0.10000000149 Episode 2520 - Mean score: 0.118200001828 Avg critic losses: tensor(9.8622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.09 0.1 ] Episode 2521 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) episode done in 68 time steps; scores: [ 0.2 0.09] Episode 2522 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2523 - Score: 0.10000000149 Avg critic losses: tensor(7.6663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2524 - Score: 0.0900000017136 Avg critic losses: tensor(9.9932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2525 - Score: 0.10000000149 Avg critic losses: tensor(9.4174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0634, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0396, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0617, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) episode done in 163 time steps; scores: [ 0.39000001 0.40000001] Episode 2526 - Score: 0.40000000596 Avg critic losses: tensor(9.2925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2527 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2528 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2529 - Score: 0.10000000149 Avg critic losses: tensor(8.1475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2530 - Score: 0.10000000149 Avg critic losses: tensor(9.7260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2531 - Score: 0.10000000149 Avg critic losses: tensor(8.4094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2532 - Score: 0.10000000149 Avg critic losses: tensor(8.0187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2533 - Score: 0.10000000149 Avg critic losses: tensor(9.6275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) episode done in 55 time steps; scores: [ 0.1 0.09] Episode 2534 - Score: 0.10000000149 Avg critic losses: tensor(9.3328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2535 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2536 - Score: 0.190000003204 Avg critic losses: tensor(7.4154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2537 - Score: 0.10000000149 Avg critic losses: tensor(9.9337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) episode done in 32 time steps; scores: [ 0.1 -0.01] Episode 2538 - Score: 0.10000000149 Avg critic losses: tensor(8.5633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0612, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2539 - Score: 0.10000000149 Avg critic losses: tensor(8.0342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2540 - Score: 0.10000000149 Episode 2540 - Mean score: 0.121400001869 Avg critic losses: tensor(7.9955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.1 0.19] Episode 2541 - Score: 0.190000003204 Avg critic losses: tensor(7.8286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2542 - Score: 0.10000000149 Avg critic losses: tensor(8.6210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2543 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0611, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.09 0.1 ] Episode 2544 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.1834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2545 - Score: 0.10000000149 Avg critic losses: tensor(6.9910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2546 - Score: 0.0900000017136 Avg critic losses: tensor(6.7648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2547 - Score: 0.10000000149 Avg critic losses: tensor(9.5482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2548 - Score: 0.10000000149 Avg critic losses: tensor(5.2621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 2549 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.09 0.1 ] Episode 2550 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 -0.01] Episode 2551 - Score: 0.10000000149 Avg critic losses: tensor(5.0111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2552 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.1 0.19] Episode 2553 - Score: 0.190000003204 Avg critic losses: tensor(9.6967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2554 - Score: 0.10000000149 Avg critic losses: tensor(4.9608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) episode done in 68 time steps; scores: [ 0.2 0.09] Episode 2555 - Score: 0.20000000298 Avg critic losses: tensor(7.9439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0432, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.1 0.09] Episode 2556 - Score: 0.10000000149 Avg critic losses: tensor(9.7526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.1 0.09] Episode 2557 - Score: 0.10000000149 Avg critic losses: tensor(7.6997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0435, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2558 - Score: 0.20000000298 Avg critic losses: tensor(7.1926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0610, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.09 0.2 ] Episode 2559 - Score: 0.20000000298 Avg critic losses: tensor(8.7881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2560 - Score: 0.10000000149 Episode 2560 - Mean score: 0.122400001884 Avg critic losses: tensor(8.4666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2561 - Score: 0.190000003204 Avg critic losses: tensor(8.4506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2562 - Score: 0.20000000298 Avg critic losses: tensor(8.8803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) episode done in 37 time steps; scores: [-0.01 0.1 ] Episode 2563 - Score: 0.10000000149 Avg critic losses: tensor(9.3719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) episode done in 57 time steps; scores: [ 0.1 0.09] Episode 2564 - Score: 0.10000000149 Avg critic losses: tensor(7.2753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.1 0.09] Episode 2565 - Score: 0.10000000149 Avg critic losses: tensor(9.6269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2566 - Score: 0.190000003204 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0434, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) episode done in 55 time steps; scores: [ 0.1 0.09] Episode 2567 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) episode done in 55 time steps; scores: [ 0.1 0.09] Episode 2568 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2569 - Score: 0.10000000149 Avg critic losses: tensor(7.7153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2570 - Score: 0.10000000149 Avg critic losses: tensor(7.5221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2571 - Score: 0.10000000149 Avg critic losses: tensor(7.6141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2572 - Score: 0.10000000149 Avg critic losses: tensor(8.7136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2573 - Score: 0.190000003204 Avg critic losses: tensor(6.0559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2574 - Score: 0.20000000298 Avg critic losses: tensor(5.9032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0620, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) episode done in 56 time steps; scores: [ 0.1 0.09] Episode 2575 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0611, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) episode done in 55 time steps; scores: [ 0.09 0.1 ] Episode 2576 - Score: 0.10000000149 Avg critic losses: tensor(7.7325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0447, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0457, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2577 - Score: 0.10000000149 Avg critic losses: tensor(8.7968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2578 - Score: 0.20000000298 Avg critic losses: tensor(9.6387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2579 - Score: 0.10000000149 Avg critic losses: tensor(9.0689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0614, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2580 - Score: 0.10000000149 Episode 2580 - Mean score: 0.123600001894 Avg critic losses: tensor(8.6905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2581 - Score: 0.10000000149 Avg critic losses: tensor(9.3190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) episode done in 83 time steps; scores: [ 0.2 0.19] Episode 2582 - Score: 0.20000000298 Avg critic losses: tensor(8.5675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2583 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.7679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0466, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2584 - Score: 0.10000000149 Avg critic losses: tensor(9.5789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2585 - Score: 0.0900000017136 Avg critic losses: tensor(9.1618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2586 - Score: 0.10000000149 Avg critic losses: tensor(9.7748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) episode done in 64 time steps; scores: [ 0.2 0.09] Episode 2587 - Score: 0.20000000298 Avg critic losses: tensor(9.5097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2588 - Score: 0.10000000149 Avg critic losses: tensor(9.5172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.1 0.09] Episode 2589 - Score: 0.10000000149 Avg critic losses: tensor(9.7619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2590 - Score: 0.0900000017136 Avg critic losses: tensor(7.3747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2591 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2592 - Score: 0.10000000149 Avg critic losses: tensor(9.2143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.09 0.2 ] Episode 2593 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0429, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0.1 -0.01] Episode 2594 - Score: 0.10000000149 Avg critic losses: tensor(6.6283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2595 - Score: 0.190000003204 Avg critic losses: tensor(8.7478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2596 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 2597 - Score: 0.0 Avg critic losses: tensor(7.3667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2598 - Score: 0.10000000149 Avg critic losses: tensor(9.3282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0431, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0451, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2599 - Score: 0.10000000149 Avg critic losses: tensor(5.0699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) episode done in 68 time steps; scores: [ 0.09 0.2 ] Episode 2600 - Score: 0.20000000298 Episode 2600 - Mean score: 0.125600001924 Avg critic losses: tensor(8.1810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.09 0.1 ] Episode 2601 - Score: 0.10000000149 Avg critic losses: tensor(9.7320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 0.09] Episode 2602 - Score: 0.10000000149 Avg critic losses: tensor(8.4718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.2 0.09] Episode 2603 - Score: 0.20000000298 Avg critic losses: tensor(9.3682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 -0.01] Episode 2604 - Score: 0.10000000149 Avg critic losses: tensor(9.0774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) episode done in 38 time steps; scores: [-0.01 0.1 ] Episode 2605 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.1 0.19] Episode 2606 - Score: 0.190000003204 Avg critic losses: tensor(7.8333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.09 0.2 ] Episode 2607 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) episode done in 65 time steps; scores: [ 0.2 0.09] Episode 2608 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) episode done in 64 time steps; scores: [ 0.1 0.19] Episode 2609 - Score: 0.190000003204 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) episode done in 37 time steps; scores: [ 0.1 -0.01] Episode 2610 - Score: 0.10000000149 Avg critic losses: tensor(9.7491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) episode done in 28 time steps; scores: [-0.01 0.1 ] Episode 2611 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2612 - Score: 0.10000000149 Avg critic losses: tensor(9.9907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0458, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.09 0.2 ] Episode 2613 - Score: 0.20000000298 Avg critic losses: tensor(8.8773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0454, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2614 - Score: 0.0900000017136 Avg critic losses: tensor(6.4887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) episode done in 65 time steps; scores: [ 0.1 0.19] Episode 2615 - Score: 0.190000003204 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) episode done in 64 time steps; scores: [ 0.2 0.09] Episode 2616 - Score: 0.20000000298 Avg critic losses: tensor(7.6306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2617 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2618 - Score: 0.10000000149 Avg critic losses: tensor(9.9232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.09 0.1 ] Episode 2619 - Score: 0.10000000149 Avg critic losses: tensor(9.6394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.09 0.1 ] Episode 2620 - Score: 0.10000000149 Episode 2620 - Mean score: 0.126200001948 Avg critic losses: tensor(9.6244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0627, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2621 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2622 - Score: 0.10000000149 Avg critic losses: tensor(9.2337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2623 - Score: 0.0900000017136 Avg critic losses: tensor(6.8689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2624 - Score: 0.10000000149 Avg critic losses: tensor(8.3502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.1 0.19] Episode 2625 - Score: 0.190000003204 Avg critic losses: tensor(6.9332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2626 - Score: 0.0900000017136 Avg critic losses: tensor(9.5993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2627 - Score: 0.0900000017136 Avg critic losses: tensor(7.2257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0462, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) episode done in 68 time steps; scores: [ 0.2 0.09] Episode 2628 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2629 - Score: 0.10000000149 Avg critic losses: tensor(9.6796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0609, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7962e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2630 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) episode done in 65 time steps; scores: [ 0.09 0.2 ] Episode 2631 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0620, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0464, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2632 - Score: 0.10000000149 Avg critic losses: tensor(9.9466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2633 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 -0.02] Episode 2634 - Score: 0.10000000149 Avg critic losses: tensor(9.9649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2635 - Score: 0.10000000149 Avg critic losses: tensor(8.9843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2636 - Score: 0.10000000149 Avg critic losses: tensor(8.1399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2637 - Score: 0.10000000149 Avg critic losses: tensor(8.7758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) episode done in 53 time steps; scores: [ 0.1 0.09] Episode 2638 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2639 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0461, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0607, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2640 - Score: 0.10000000149 Episode 2640 - Mean score: 0.123000001907 Avg critic losses: tensor(7.4034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2641 - Score: 0.10000000149 Avg critic losses: tensor(7.3158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [-0.01 0.1 ] Episode 2642 - Score: 0.10000000149 Avg critic losses: tensor(8.6535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.09 0.1 ] Episode 2643 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2644 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.1 0.09] Episode 2645 - Score: 0.10000000149 Avg critic losses: tensor(8.8797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2646 - Score: 0.10000000149 Avg critic losses: tensor(6.2850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2647 - Score: 0.10000000149 Avg critic losses: tensor(7.7328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) episode done in 89 time steps; scores: [ 0.09 0.2 ] Episode 2648 - Score: 0.20000000298 Avg critic losses: tensor(9.5033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2649 - Score: 0.10000000149 Avg critic losses: tensor(7.3626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2650 - Score: 0.10000000149 Avg critic losses: tensor(9.9329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2651 - Score: 0.10000000149 Avg critic losses: tensor(7.1379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) episode done in 33 time steps; scores: [ 0.1 -0.01] Episode 2652 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2653 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2654 - Score: 0.10000000149 Avg critic losses: tensor(9.3920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5833e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2655 - Score: 0.10000000149 Avg critic losses: tensor(8.6976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0617, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2656 - Score: 0.10000000149 Avg critic losses: tensor(5.3404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [-0.01 0.1 ] Episode 2657 - Score: 0.10000000149 Avg critic losses: tensor(8.3812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0453, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2658 - Score: 0.10000000149 Avg critic losses: tensor(9.0305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2659 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [-0.01 0.1 ] Episode 2660 - Score: 0.10000000149 Episode 2660 - Mean score: 0.120300001856 Avg critic losses: tensor(7.6871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) episode done in 53 time steps; scores: [ 0.1 0.09] Episode 2661 - Score: 0.10000000149 Avg critic losses: tensor(8.4035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2662 - Score: 0.0900000017136 Avg critic losses: tensor(6.9712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2663 - Score: 0.10000000149 Avg critic losses: tensor(8.2177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2664 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3588e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2665 - Score: 0.10000000149 Avg critic losses: tensor(7.6171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2666 - Score: 0.10000000149 Avg critic losses: tensor(6.1115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 0.09] Episode 2667 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0607, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 0.09] Episode 2668 - Score: 0.10000000149 Avg critic losses: tensor(9.9067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0611, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 0.09] Episode 2669 - Score: 0.10000000149 Avg critic losses: tensor(9.3004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2670 - Score: 0.10000000149 Avg critic losses: tensor(9.6141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0609, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) episode done in 72 time steps; scores: [ 0.09 0.2 ] Episode 2671 - Score: 0.20000000298 Avg critic losses: tensor(6.9988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0613, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0616, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) episode done in 89 time steps; scores: [ 0.19 0.2 ] Episode 2672 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2673 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0610, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2674 - Score: 0.0900000017136 Avg critic losses: tensor(8.9906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2675 - Score: 0.10000000149 Avg critic losses: tensor(8.9029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0627, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3294e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0614, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0637, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2676 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0653, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0644, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) episode done in 40 time steps; scores: [-0.01 0.1 ] Episode 2677 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0467, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0610, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0611, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0617, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) episode done in 122 time steps; scores: [ 0.2 0.19] Episode 2678 - Score: 0.20000000298 Avg critic losses: tensor(7.5229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0614, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1621e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0609, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.1 0.09] Episode 2679 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0617, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2680 - Score: 0.10000000149 Episode 2680 - Mean score: 0.117400001809 Avg critic losses: tensor(5.5111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2681 - Score: 0.0900000017136 Avg critic losses: tensor(8.6850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0610, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2682 - Score: 0.10000000149 Avg critic losses: tensor(8.6010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) episode done in 49 time steps; scores: [ 0.1 -0.01] Episode 2683 - Score: 0.10000000149 Avg critic losses: tensor(9.9398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4829e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0459, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0646, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0607, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2684 - Score: 0.10000000149 Avg critic losses: tensor(8.5761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0631, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0465, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0628, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0607, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0613, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.1 -0.01] Episode 2685 - Score: 0.10000000149 Avg critic losses: tensor(6.7552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8235e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0615, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0.1 -0.01] Episode 2686 - Score: 0.10000000149 Avg critic losses: tensor(9.2992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2687 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2688 - Score: 0.0900000017136 Avg critic losses: tensor(6.8718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2689 - Score: 0.10000000149 Avg critic losses: tensor(8.5934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0625, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6040e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) episode done in 94 time steps; scores: [ 0.09 0.2 ] Episode 2690 - Score: 0.20000000298 Avg critic losses: tensor(6.1127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0647, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2691 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0607, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2692 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0617, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2693 - Score: 0.0900000017136 Avg critic losses: tensor(8.7842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0621, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0623, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.09 0.1 ] Episode 2694 - Score: 0.10000000149 Avg critic losses: tensor(9.8496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0641, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2695 - Score: 0.10000000149 Avg critic losses: tensor(7.7623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6597e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1380e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0615, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0628, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2696 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2697 - Score: 0.10000000149 Avg critic losses: tensor(8.2363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0613, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2698 - Score: 0.0900000017136 Avg critic losses: tensor(7.1788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2699 - Score: 0.10000000149 Avg critic losses: tensor(5.9657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0612, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0635, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2700 - Score: 0.10000000149 Episode 2700 - Mean score: 0.114400001764 Avg critic losses: tensor(6.7404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2701 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2702 - Score: 0.10000000149 Avg critic losses: tensor(6.6911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0610, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0613, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2703 - Score: 0.10000000149 Avg critic losses: tensor(9.2605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0614, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0612, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2704 - Score: 0.10000000149 Avg critic losses: tensor(7.8156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2705 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0609, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2706 - Score: 0.10000000149 Avg critic losses: tensor(7.3100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1503e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) episode done in 53 time steps; scores: [ 0.09 0.1 ] Episode 2707 - Score: 0.10000000149 Avg critic losses: tensor(7.3153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2708 - Score: 0.0900000017136 Avg critic losses: tensor(5.2966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0637, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2709 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4219e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2710 - Score: 0.0900000017136 Avg critic losses: tensor(7.8002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0628, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1370e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2711 - Score: 0.10000000149 Avg critic losses: tensor(8.0690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0639, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5061e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2712 - Score: 0.10000000149 Avg critic losses: tensor(9.0241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2713 - Score: 0.10000000149 Avg critic losses: tensor(7.8750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0618, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0636, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0616, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0613, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0641, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0622, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0649, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0625, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0607, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8819e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) episode done in 205 time steps; scores: [ 0.50000001 0.39000001] Episode 2714 - Score: 0.500000007451 Avg critic losses: tensor(8.6860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0857e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0633, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2715 - Score: 0.10000000149 Avg critic losses: tensor(8.8705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0610, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0614, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2716 - Score: 0.10000000149 Avg critic losses: tensor(9.2641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6830e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2993e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2717 - Score: 0.10000000149 Avg critic losses: tensor(8.9468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0634, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0637, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0611, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.1 0.19] Episode 2718 - Score: 0.190000003204 Avg critic losses: tensor(8.2140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2719 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0647, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0626, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6926e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) episode done in 48 time steps; scores: [ 0.2 -0.01] Episode 2720 - Score: 0.20000000298 Episode 2720 - Mean score: 0.11260000173 Avg critic losses: tensor(8.2162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0614, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0614, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2721 - Score: 0.10000000149 Avg critic losses: tensor(8.4569e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0612, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0613, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2722 - Score: 0.10000000149 Avg critic losses: tensor(9.8448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0628, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0614, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0615, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.1 0.09] Episode 2723 - Score: 0.10000000149 Avg critic losses: tensor(8.2121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0617, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0631, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9423e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) episode done in 67 time steps; scores: [ 0.09 0.1 ] Episode 2724 - Score: 0.10000000149 Avg critic losses: tensor(6.6593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0636, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2725 - Score: 0.10000000149 Avg critic losses: tensor(6.1486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7537e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0617, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0.1 -0.01] Episode 2726 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0612, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0614, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0612, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5446e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) episode done in 32 time steps; scores: [-0.01 0.1 ] Episode 2727 - Score: 0.10000000149 Avg critic losses: tensor(6.9636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0609, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9898e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0622, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.09 0.1 ] Episode 2728 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0610, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0630, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2729 - Score: 0.10000000149 Avg critic losses: tensor(8.9135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0611, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8852e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0626, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1594e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4826e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0649, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0686, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2730 - Score: 0.10000000149 Avg critic losses: tensor(9.4512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0615, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0607, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0607, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0624, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2731 - Score: 0.10000000149 Avg critic losses: tensor(9.0416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0638, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0611, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0607, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2732 - Score: 0.10000000149 Avg critic losses: tensor(8.7344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0611, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0621, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. -0.01] Episode 2733 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2734 - Score: 0.0900000017136 Avg critic losses: tensor(9.9811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1075e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0625, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2735 - Score: 0.10000000149 Avg critic losses: tensor(8.2918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0607, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0610, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2736 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6904e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4749e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0610, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) episode done in 53 time steps; scores: [ 0.1 0.09] Episode 2737 - Score: 0.10000000149 Avg critic losses: tensor(7.9016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0610, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0617, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8714e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0622, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0628, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2738 - Score: 0.10000000149 Avg critic losses: tensor(8.9638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2739 - Score: 0.10000000149 Avg critic losses: tensor(7.5275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0616, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9451e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.09 0.1 ] Episode 2740 - Score: 0.10000000149 Episode 2740 - Mean score: 0.108900001664 Avg critic losses: tensor(9.2499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0652, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0610, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) episode done in 54 time steps; scores: [ 0.1 -0.01] Episode 2741 - Score: 0.10000000149 Avg critic losses: tensor(9.3439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3419e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0638, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) episode done in 52 time steps; scores: [ 0.09 0.1 ] Episode 2742 - Score: 0.10000000149 Avg critic losses: tensor(7.8360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0614, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2778e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2743 - Score: 0.10000000149 Avg critic losses: tensor(7.9389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2744 - Score: 0.10000000149 Avg critic losses: tensor(7.3469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8371e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0617, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) episode done in 69 time steps; scores: [ 0.2 0.09] Episode 2745 - Score: 0.20000000298 Avg critic losses: tensor(8.4187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0611, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2746 - Score: 0.10000000149 Avg critic losses: tensor(8.8574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0626, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0611, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0609, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2747 - Score: 0.10000000149 Avg critic losses: tensor(7.1492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0613, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2748 - Score: 0.10000000149 Avg critic losses: tensor(7.8141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0613, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0607, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7783e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2749 - Score: 0.10000000149 Avg critic losses: tensor(8.9603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0607, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2750 - Score: 0.10000000149 Avg critic losses: tensor(8.7301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0629, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2751 - Score: 0.10000000149 Avg critic losses: tensor(8.3986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0612, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2794e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2752 - Score: 0.10000000149 Avg critic losses: tensor(8.9253e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4117e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0607, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0614, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2753 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0612, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0617, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 0.09] Episode 2754 - Score: 0.10000000149 Avg critic losses: tensor(8.4082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0642, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0613, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2755 - Score: 0.10000000149 Avg critic losses: tensor(9.6998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5382e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2756 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2757 - Score: 0.10000000149 Avg critic losses: tensor(9.8520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0609, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2758 - Score: 0.10000000149 Avg critic losses: tensor(7.9344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0609, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [-0.01 0.1 ] Episode 2759 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6495e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0609, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0617, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2760 - Score: 0.10000000149 Episode 2760 - Mean score: 0.109000001661 Avg critic losses: tensor(8.9482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0613, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0614, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2761 - Score: 0.10000000149 Avg critic losses: tensor(8.5827e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0622, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5518e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6277e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2762 - Score: 0.0900000017136 Avg critic losses: tensor(9.5352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9883e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2763 - Score: 0.10000000149 Avg critic losses: tensor(8.3525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0614, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7340e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0616, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) episode done in 70 time steps; scores: [ 0.1 0.19] Episode 2764 - Score: 0.190000003204 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9727e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2765 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0623, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2766 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0609, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8390e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8199e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2767 - Score: 0.10000000149 Avg critic losses: tensor(9.0961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0619, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2768 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0607, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0607, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 0.09] Episode 2769 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0607, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6436e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0613, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2770 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4426e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2771 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2772 - Score: 0.10000000149 Avg critic losses: tensor(6.4398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0611, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2773 - Score: 0.10000000149 Avg critic losses: tensor(8.6570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5550e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3264e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4677e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0681e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5231e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4185e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.09 0.2 ] Episode 2774 - Score: 0.20000000298 Avg critic losses: tensor(7.0553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0614, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3192e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2775 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0372e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2776 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0624, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2777 - Score: 0.10000000149 Avg critic losses: tensor(8.8120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2778 - Score: 0.10000000149 Avg critic losses: tensor(5.6801e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4788e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0609, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8693e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0615, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) episode done in 69 time steps; scores: [ 0.1 0.09] Episode 2779 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4437e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7449e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4440e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2780 - Score: 0.0900000017136 Episode 2780 - Mean score: 0.107700001653 Avg critic losses: tensor(7.3721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2781 - Score: 0.0900000017136 Avg critic losses: tensor(6.0805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0609, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5188e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2782 - Score: 0.10000000149 Avg critic losses: tensor(6.3632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1460e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4044e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0002, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7327e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) episode done in 70 time steps; scores: [ 0.2 0.09] Episode 2783 - Score: 0.20000000298 Avg critic losses: tensor(6.7583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8109e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8105e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0614, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0614, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2784 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) episode done in 89 time steps; scores: [ 0.09 0.2 ] Episode 2785 - Score: 0.20000000298 Avg critic losses: tensor(9.8243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6623e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2786 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1133e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9991e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2787 - Score: 0.0900000017136 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2788 - Score: 0.10000000149 Avg critic losses: tensor(9.3694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5665e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2124e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2257e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2172e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2789 - Score: 0.10000000149 Avg critic losses: tensor(6.5574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6046e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9067e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0144e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3618e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) episode done in 53 time steps; scores: [ 0.09 0.1 ] Episode 2790 - Score: 0.10000000149 Avg critic losses: tensor(7.5157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0094e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5676e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.3218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2636e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3764e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0.1 -0.01] Episode 2791 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8408e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5563e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8682e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2182e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4541e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) episode done in 48 time steps; scores: [ 0.09 0.1 ] Episode 2792 - Score: 0.10000000149 Avg critic losses: tensor(9.7861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3090e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0450, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2793 - Score: 0.10000000149 Avg critic losses: tensor(8.4404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0187e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7461e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) episode done in 68 time steps; scores: [ 0.2 0.09] Episode 2794 - Score: 0.20000000298 Avg critic losses: tensor(7.8901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9259e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5799e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0404e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2795 - Score: 0.10000000149 Avg critic losses: tensor(6.9613e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1612e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0901e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0619, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8229e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7649e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 0.09] Episode 2796 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6324e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1400e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2797 - Score: 0.10000000149 Avg critic losses: tensor(8.5592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6988e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0475, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9353e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2798 - Score: 0.10000000149 Avg critic losses: tensor(7.3843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0617, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0621, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9732e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2799 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9869e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2800 - Score: 0.10000000149 Episode 2800 - Mean score: 0.109900001679 Avg critic losses: tensor(5.4634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9965e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2801 - Score: 0.10000000149 Avg critic losses: tensor(9.1970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0670e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9141e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) episode done in 31 time steps; scores: [ 0.1 -0.01] Episode 2802 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7625e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0947e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2803 - Score: 0.10000000149 Avg critic losses: tensor(5.9266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9081e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0446, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2804 - Score: 0.10000000149 Avg critic losses: tensor(9.6742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8435e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2396e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8939e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2805 - Score: 0.10000000149 Avg critic losses: tensor(8.4345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7736e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7692e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3378e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0623, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4555e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6558e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2806 - Score: 0.190000003204 Avg critic losses: tensor(6.9180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0142e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9790e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5713e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1033e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2807 - Score: 0.10000000149 Avg critic losses: tensor(7.3664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7961e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4800e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0570e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6173e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2808 - Score: 0.10000000149 Avg critic losses: tensor(9.5689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4948e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) episode done in 14 time steps; scores: [-0.01 0. ] Episode 2809 - Score: 0.0 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1302e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0596, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0603, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2468e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2810 - Score: 0.0900000017136 Avg critic losses: tensor(9.8065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2846e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7021e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4131e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2811 - Score: 0.10000000149 Avg critic losses: tensor(5.9969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0339e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8561e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2812 - Score: 0.10000000149 Avg critic losses: tensor(9.0858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6388e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4479e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1473e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2398e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2813 - Score: 0.10000000149 Avg critic losses: tensor(8.2924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4699e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0740e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5420e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1197e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4319e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5366e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5839e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1445e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0700e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2814 - Score: 0.10000000149 Avg critic losses: tensor(9.3102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9608e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1269e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9493e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2211e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [-0.01 0.1 ] Episode 2815 - Score: 0.10000000149 Avg critic losses: tensor(8.1955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2239e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2001e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5592e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2816 - Score: 0.10000000149 Avg critic losses: tensor(8.7958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2204e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9861e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8614e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4290e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2817 - Score: 0.10000000149 Avg critic losses: tensor(8.8650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1114e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1691e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2818 - Score: 0.10000000149 Avg critic losses: tensor(7.8043e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6176e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2208e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2819 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2858e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8787e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1499e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9143e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3106e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1267e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2820 - Score: 0.10000000149 Episode 2820 - Mean score: 0.104000001587 Avg critic losses: tensor(6.9389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5553e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9376e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1750e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0156e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1906e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2261e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0384e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2821 - Score: 0.10000000149 Avg critic losses: tensor(7.2089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6716e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5480e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2822 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0448e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4174e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6397e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6146e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1121e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1492e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0443, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2823 - Score: 0.10000000149 Avg critic losses: tensor(8.0485e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9776e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7195e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1309e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0718e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3914e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2824 - Score: 0.10000000149 Avg critic losses: tensor(7.1034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3959e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(2.8527e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4756e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0547e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9430e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4422e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4557e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0508e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8921e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7405e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) episode done in 68 time steps; scores: [ 0.2 0.09] Episode 2825 - Score: 0.20000000298 Avg critic losses: tensor(9.8070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6202e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2696e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9564e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5256e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8770e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7970e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4262e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5684e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4928e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8834e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4659e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1215e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5620e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6171e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1831e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8642e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1931e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1132e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8580e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2836e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4905e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5005e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6343e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7633e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7663e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7053e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6058e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) episode done in 106 time steps; scores: [ 0.3 0.19] Episode 2826 - Score: 0.30000000447 Avg critic losses: tensor(6.5411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3748e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8916e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1456e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2079e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2063e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0304e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2827 - Score: 0.10000000149 Avg critic losses: tensor(7.7155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1813e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7710e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4472e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2428e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2249e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8769e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7049e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4463e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3871e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7155e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0844e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1540e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4399e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0792e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) episode done in 69 time steps; scores: [ 0.2 0.09] Episode 2828 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9096e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4137e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5919e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2829 - Score: 0.10000000149 Avg critic losses: tensor(7.2140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4212e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8307e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1726e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1888e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3583e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6205e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0816e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1047e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5379e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2830 - Score: 0.10000000149 Avg critic losses: tensor(7.7752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7341e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2498e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3115e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1915e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1867e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2942e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2831 - Score: 0.10000000149 Avg critic losses: tensor(7.3849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8458e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8118e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0282e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2413e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5464e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4224e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3595e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2832 - Score: 0.10000000149 Avg critic losses: tensor(9.6519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8180e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1313e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6648e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6811e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0837e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2833 - Score: 0.10000000149 Avg critic losses: tensor(7.3265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1070e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9018e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6336e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1585e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3490e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3575e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3476e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9206e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3786e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5723e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1531e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5528e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2509e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.9364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1657e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8940e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2511e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6333e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2854e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2348e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) episode done in 86 time steps; scores: [ 0.1 0.19] Episode 2834 - Score: 0.190000003204 Avg critic losses: tensor(6.6478e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2236e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6497e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1951e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1477e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2157e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2753e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3303e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3935e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7542e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6717e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4285e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1136e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3179e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6661e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5432e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0086e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7822e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5196e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8701e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5083e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0600, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6773e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) episode done in 68 time steps; scores: [ 0.1 0.09] Episode 2835 - Score: 0.10000000149 Avg critic losses: tensor(7.8082e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5603e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5730e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3964e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1985e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7881e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2836 - Score: 0.10000000149 Avg critic losses: tensor(9.3850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0754e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0468, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0177e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7406e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2837 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6815e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7733e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7056e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7534e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3944e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2838 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4019e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5298e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4611e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6213e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0609, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2927e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8389e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4135e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6729e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6994e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1953e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1640e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4885e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2346e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0463, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5886e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1887e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5972e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8292e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5731e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1784e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) episode done in 70 time steps; scores: [ 0.1 0.19] Episode 2839 - Score: 0.190000003204 Avg critic losses: tensor(7.8894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1002e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0918e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5743e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4842e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9907e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2840 - Score: 0.10000000149 Episode 2840 - Mean score: 0.110900001694 Avg critic losses: tensor(7.0373e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5310e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0583, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9957e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0076e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4218e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0358e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7434e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9000e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.5026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8734e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2627e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8890e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9895e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4679e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2841 - Score: 0.10000000149 Avg critic losses: tensor(7.5849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2517e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5395e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6486e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4810e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2842 - Score: 0.10000000149 Avg critic losses: tensor(9.6193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0707e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4241e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.2524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0455, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0473, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6777e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7227e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1123e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5572e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9482e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1107e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0608, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8744e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2843 - Score: 0.10000000149 Avg critic losses: tensor(8.4551e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0573e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.6120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4015e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9429e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4520e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3279e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0586, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1672e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5979e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0698e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4270e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8963e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2844 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8352e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2747e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8631e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0589, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4669e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3010e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5680e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2960e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7296e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5494e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9374e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1306e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2845 - Score: 0.0900000017136 Avg critic losses: tensor(5.7617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7354e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8828e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3874e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8847e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7154e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6978e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9475e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2846 - Score: 0.10000000149 Avg critic losses: tensor(7.3326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0671e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4054e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0602, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2724e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0864e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6266e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0632e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2483e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1711e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8100e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8719e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8998e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9802e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0615, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0892e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7530e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1036e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0252e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2847 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0923e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4568e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4545e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1011e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4223e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2004e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1038e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6634e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8878e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5120e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9280e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2609e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2848 - Score: 0.10000000149 Avg critic losses: tensor(8.2394e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0617e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9662e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9462e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4364e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2525e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0291e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8865e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6409e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8350e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0950e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3377e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2849 - Score: 0.10000000149 Avg critic losses: tensor(7.2968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6952e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7678e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9876e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4315e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0275e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0469, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3088e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9552e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) episode done in 32 time steps; scores: [ 0.1 -0.01] Episode 2850 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9034e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4254e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1873e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9843e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2035e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7305e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1571e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0930e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2911e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5793e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3272e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8488e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6739e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6016e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1974e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7201e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8868e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7532e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8095e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7897e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5708e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0646e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0590, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8704e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7125e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3804e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9444e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8203e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4791e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5501e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1048e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1880e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) episode done in 65 time steps; scores: [ 0.2 0.09] Episode 2851 - Score: 0.20000000298 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2785e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5017e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5112e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7012e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8980e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5658e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4417e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3593e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9599e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7706e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2922e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2852 - Score: 0.10000000149 Avg critic losses: tensor(9.3237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6515e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0287e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4258e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6427e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4237e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4003e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7688e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7465e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0301e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4821e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5178e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3533e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4694e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7151e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4116e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0853e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3859e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.9875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0101e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4470e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0477, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2325e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7607e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2720e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0598, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8971e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9877e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0610e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 0.09] Episode 2853 - Score: 0.10000000149 Avg critic losses: tensor(9.8078e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8667e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2344e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1849e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3781e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1167e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3912e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8835e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0041e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8084e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6893e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0359e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1674e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5392e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5039e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.4375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1129e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5725e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2854 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1139e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8424e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5958e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5391e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2037e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1127e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7284e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1338e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9543e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7247e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4908e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8243e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7582e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3471e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0. 0.09] Episode 2855 - Score: 0.0900000017136 Avg critic losses: tensor(8.6274e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8728e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0576, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3523e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0617, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4066e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8929e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9856e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4335e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9796e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8334e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8689e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5862e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0470, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8009e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4402e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0626e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2856 - Score: 0.10000000149 Avg critic losses: tensor(8.5882e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8630e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8709e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.4955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6795e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6616e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9997e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8986e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7818e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7260e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0411e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7057e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4014e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5045e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8590e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [-0.01 0.1 ] Episode 2857 - Score: 0.10000000149 Avg critic losses: tensor(9.4314e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8110e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8165e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9762e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4954e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3453e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1281e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8289e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8556e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4489e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0814e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4355e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5152e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7351e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1337e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0595, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5920e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2051e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8712e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5666e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1685e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2159e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0760e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8806e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4029e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0594, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8774e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1637e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8803e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9383e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4322e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4780e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7807e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3738e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4742e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6767e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3768e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9870e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1825e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0472, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) episode done in 63 time steps; scores: [ 0.1 0.19] Episode 2858 - Score: 0.190000003204 Avg critic losses: tensor(9.0221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0508, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8546e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0840e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3981e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.5715e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5574e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0457e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3060e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5516e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6771e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0263e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8845e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2879e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1030e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8549e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6968e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6308e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2859 - Score: 0.10000000149 Avg critic losses: tensor(7.9226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0300e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5519e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1824e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9502e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4357e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5982e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4184e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1820e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8191e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1332e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0652e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9164e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1746e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0941e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6169e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7615e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0875e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8347e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2361e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8455e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3245e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3977e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2207e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7673e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4242e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5721e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) episode done in 51 time steps; scores: [ 0.09 0.1 ] Episode 2860 - Score: 0.10000000149 Episode 2860 - Mean score: 0.111600001715 Avg critic losses: tensor(9.2255e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4755e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9271e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7973e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1008e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5265e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3789e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1596e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9655e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3536e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0617, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9635e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3535e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5443e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5560e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7512e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8917e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2996e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7924e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9022e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0766e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1619e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9369e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0601, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7454e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6102e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9130e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4782e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3459e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5695e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0166e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) episode done in 50 time steps; scores: [ 0.1 0.09] Episode 2861 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0476, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1312e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0613, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5848e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2438e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4943e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7356e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6064e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7320e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8099e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0175e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6812e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7851e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0222e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2932e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0499, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2418e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8894e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6752e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4703e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2862 - Score: 0.10000000149 Avg critic losses: tensor(9.5071e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1506e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3514e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1761e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2119e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6020e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0617, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2386e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8554e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5938e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0527, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7450e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7329e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.1421e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0375e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3286e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5365e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0013e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.0466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7989e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2244e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0577e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8758e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2024e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2863 - Score: 0.10000000149 Avg critic losses: tensor(7.1006e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8104e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5220e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5087e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7690e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9687e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3805e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.6909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6779e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0507, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9317e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6522e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7660e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2158e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7686e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6385e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1628e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6987e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6055e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9147e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0316e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0488, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3214e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3683e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0. 0.09] Episode 2864 - Score: 0.0900000017136 Avg critic losses: tensor(9.2194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8162e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.3091e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0956e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1510e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5225e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4149e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6909e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1484e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5328e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9855e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9775e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.8226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7342e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0571, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3092e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5548e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8200e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2865 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9138e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0492, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6122e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7866e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(3.8513e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0498, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9381e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8538e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0491e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2832e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1234e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5629e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8111e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1925e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7469e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5984e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9362e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6050e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4387e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2283e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4933e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0510, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1431e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9576e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7031e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8148e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1433e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8080e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4250e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8474e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8295e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7638e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1407e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7161e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0113e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.4293e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0540, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2403e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6539e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6027e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7559e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7624e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9604e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4741e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9321e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3238e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0521, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2198e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0487, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.1 0.19] Episode 2866 - Score: 0.190000003204 Avg critic losses: tensor(7.7797e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3074e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4675e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4032e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8937e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0525, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0654e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0534, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9230e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6900e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8526e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1976e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9651e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2817e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6140e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0097e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8581e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9622e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2062e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9643e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0360e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6808e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6393e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1500e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0490, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5216e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7945e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [-0.01 0.1 ] Episode 2867 - Score: 0.10000000149 Avg critic losses: tensor(7.6331e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8134e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0504, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1028e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4181e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7896e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3103e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2975e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3903e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) episode done in 15 time steps; scores: [-0.01 0. ] Episode 2868 - Score: 0.0 Avg critic losses: tensor(8.8584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1757e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1126e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0493, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0150e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0999e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8579e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3246e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0186e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2587e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0569, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0023e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4278e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5735e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3644e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3268e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7653e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0486, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4414e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3891e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0478, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0474, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0548, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2650e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0482, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4288e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0587, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.8969e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0481, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.9093e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0456, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7605e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0567e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0609, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9481e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8412e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0460, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8168e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6108e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2276e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0311e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7077e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9598e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9330e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0641e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0501, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6992e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9416e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8983e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0479, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2318e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0512, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0578, grad_fn=<MeanBackward0>) episode done in 65 time steps; scores: [ 0.1 0.19] Episode 2869 - Score: 0.190000003204 Avg critic losses: tensor(8.3722e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0467e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1073e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0483, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.7934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0410e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0577, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0600e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0480, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7562e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.3936e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0593, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3606e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5910e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.2326e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4529e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5439e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0592, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7966e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5128e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0363e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.2913e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6190e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8226e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0516, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3042e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3702e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5183e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0520, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) episode done in 30 time steps; scores: [ 0.1 -0.01] Episode 2870 - Score: 0.10000000149 Avg critic losses: tensor(7.7209e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2065e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2745e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2889e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0552, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5425e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0551, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9415e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1967e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0597, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1072e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0556, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2809e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2841e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7601e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0502, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0605, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4668e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0872e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9145e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0565, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5737e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0949e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4068e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9823e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.1345e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6232e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0484, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4578e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8902e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1170e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3566e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0606, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0570, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0562, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5589e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0513, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7524e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.5586e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6664e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0555, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3221e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.8367e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0549, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2772e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1505e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0524, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.4368e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0529, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0566, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.6025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0581, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0574, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9639e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.2441e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0505, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0535, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.9507e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0514, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0647e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0515, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2228e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0558, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2442e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.2584e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9763e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0491, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.8697e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2863e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0531, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6995e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5751e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0544, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4934e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0582, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0500, grad_fn=<MeanBackward0>) episode done in 66 time steps; scores: [ 0.2 0.09] Episode 2871 - Score: 0.20000000298 Avg critic losses: tensor(8.5251e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0572, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.9248e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5798e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0526, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.9765e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.2163e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.0990e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0553, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6850e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0518, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0602e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1233e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0533, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7759e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0584, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3297e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0575, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3210e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0495, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0591e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0559, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.3085e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0591, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0557, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1193e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0069e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0530, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.6955e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0519, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9299e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.0194e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0541, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7565e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0546, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5487e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0471, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6447e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0563, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7273e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0585, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4007e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0538, grad_fn=<MeanBackward0>) episode done in 29 time steps; scores: [ 0.1 -0.01] Episode 2872 - Score: 0.10000000149 Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0503, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7160e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0543, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7189e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0599, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3860e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0528, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0580, grad_fn=<MeanBackward0>) Avg critic losses: tensor(5.0521e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0485, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.6884e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0497, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.5052e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0506, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0560, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.0946e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0561, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.8899e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.4059e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0539, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0511, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7656e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0517, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0098e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0604, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.6026e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0554, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.7496e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0542, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.9323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0564, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.8838e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0522, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.1089e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0494, grad_fn=<MeanBackward0>) Avg critic losses: tensor(4.7452e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0547, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3217e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0568, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.1323e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0509, grad_fn=<MeanBackward0>) Avg critic losses: tensor(9.5466e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0496, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.7240e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0536, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.4025e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0573, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.5504e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0588, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.7645e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0532, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0537, grad_fn=<MeanBackward0>) Avg critic losses: tensor(6.7401e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0545, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.3349e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0550, grad_fn=<MeanBackward0>) Avg critic losses: tensor(8.0153e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0452, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.1544e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0523, grad_fn=<MeanBackward0>) Avg critic losses: tensor(7.3705e-05, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0489, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0567, grad_fn=<MeanBackward0>) Avg critic losses: tensor(0.0001, grad_fn=<MeanBackward0>) Avg actor losses: tensor(-0.0579, grad_fn=<